diff --git a/README.md b/README.md index dc83f67..6ab2493 100644 --- a/README.md +++ b/README.md @@ -2,6 +2,14 @@ This project provides pre-built containers (“toolboxes”) for running LLMs on **AMD Ryzen AI Max “Strix Halo”** integrated GPUs. Toolbx is the standard developer container system in Fedora (and now works on Ubuntu, openSUSE, Arch, etc). +## ✅ Stable Configuration + +- **OS**: Fedora 42/43 +- **Linux Kernel**: 6.18.3-200 +- **Linux Firmware**: 20251111 + +This is currently the most stable setup. Switching to newer kernels, such as 6.18.4 breaks all versions of ROCm but the cutting edge nightly builds from TheRock. + ## 🚨 Updates — 2026-01-10 - **Simplified Offering**: Removed `rocwmma` containers as standard kernels in newer `llama.cpp` are now faster and stable. diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 01ffab8..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | pp512 | 80.08 ± 0.03 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | tg128 | 2.70 ± 0.14 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index a63074a..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 6.90 ± 0.00 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 0.72 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 14318e4..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | pp512 | 78.81 ± 0.04 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | tg128 | 2.71 ± 0.13 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index a63074a..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 6.90 ± 0.00 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 0.72 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 56b6c4b..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | pp512 | 73.15 ± 0.02 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | tg128 | 2.81 ± 0.14 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index e2939c5..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 7.28 ± 0.00 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 0.61 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index b8a0d9d..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | pp512 | 73.91 ± 0.04 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | tg128 | 2.75 ± 0.21 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 5ec3925..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 7.24 ± 0.00 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 0.61 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 3eb2ca3..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | pp512 | 79.77 ± 0.04 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | tg128 | 2.86 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index e006c01..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 9.04 ± 0.00 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 0.68 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 5726aaf..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | pp512 | 78.60 ± 0.02 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 1 | 0 | tg128 | 2.83 ± 0.03 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 2662197..0000000 --- a/benchmark/results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 9.06 ± 0.00 | -| llama ?B Q4_K - Medium | 70.31 GiB | 125.03 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 0.68 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 62546fa..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 275.09 ± 0.35 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.72 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 98503f5..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 13.65 ± 0.00 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.70 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 2e6dbb7..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 303.19 ± 1.30 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.71 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 888e430..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 13.90 ± 0.00 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.70 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index d124aa9..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 188.28 ± 0.38 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 22.62 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index f228ebe..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,18 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 14.50 ± 0.00 | -/opt/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:96: ROCm error -/usr/local/lib64/libggml-base.so.0(+0x35a5) [0x7fecd3ac85a5] -/usr/local/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7fecd3ac896b] -/usr/local/lib64/libggml-base.so.0(ggml_abort+0x11f) [0x7fecd3ac8aef] -/usr/local/lib64/libggml-hip.so.0(+0x2ca3912) [0x7fecd6828912] -/usr/local/lib64/libggml-hip.so.0(+0x2ca8cde) [0x7fecd682dcde] -/usr/local/lib64/libggml-base.so.0(ggml_backend_sched_synchronize+0x2e) [0x7fecd3adfe5e] -/usr/local/lib64/libllama.so.0(_ZN13llama_context11synchronizeEv+0x10) [0x7fecd6f07630] -/usr/local/bin/llama-bench() [0x408ca6] -/lib64/libc.so.6(+0x35b5) [0x7fecd345e5b5] -/lib64/libc.so.6(__libc_start_main+0x88) [0x7fecd345e668] -/usr/local/bin/llama-bench() [0x409cf5] -✖ ! [rocm-7alpha-rocwmma] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__fa1 __longctx32768 failed (exit 0) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 0740976..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 234.18 ± 1.90 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 22.63 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index d395d0e..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 14.74 ± 0.00 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.38 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 579f66a..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 273.31 ± 0.52 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.70 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index a898e0f..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 18.48 ± 0.00 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.58 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 83e7914..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 299.53 ± 0.59 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.68 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 63c2f73..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 18.59 ± 0.00 | -| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.58 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 765eb4b..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 150.46 ± 0.44 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.55 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index e76112f..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 12.78 ± 0.00 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.66 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index fcd921d..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 193.25 ± 0.21 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.55 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index dab13f2..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 13.69 ± 0.00 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.66 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 53dc835..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 88.49 ± 0.23 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.65 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 021cc0b..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 13.47 ± 0.00 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.34 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 5596703..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 152.24 ± 0.60 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.63 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 949204a..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 14.35 ± 0.00 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.34 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 2adccde..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 145.30 ± 0.23 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.51 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 411b110..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 17.44 ± 0.00 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.54 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 595ae34..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | pp512 | 185.77 ± 0.97 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.50 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 8b9e55a..0000000 --- a/benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 18.15 ± 0.00 | -| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.55 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index c2291f8..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | pp512 | 147.48 ± 0.05 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.78 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 9953ee2..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 11.84 ± 0.00 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.08 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index c76ae37..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | pp512 | 145.63 ± 0.10 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.78 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 9eaed87..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 11.77 ± 0.00 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.07 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index bf2412f..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | pp512 | 67.04 ± 0.02 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 6a07f56..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 11.46 ± 0.00 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 0.80 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 0028609..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | pp512 | 66.63 ± 0.03 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index ec2902c..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 11.47 ± 0.00 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 0.80 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 1719fa5..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | pp512 | 146.76 ± 0.06 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 77e5068..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 16.13 ± 0.00 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.06 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 0f59b59..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | pp512 | 145.07 ± 0.15 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index e4e01b6..0000000 --- a/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 16.14 ± 0.00 | -| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 1.06 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 02d1090..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | pp512 | 792.51 ± 3.25 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | tg128 | 8.47 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 3c18947..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 54.31 ± 0.00 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 5.48 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 25abb2c..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | pp512 | 794.81 ± 3.31 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | tg128 | 8.47 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 58d6ce3..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 53.85 ± 0.00 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 5.49 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 1fd1388..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | pp512 | 789.37 ± 1.53 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | tg128 | 8.48 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index f4eb292..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 58.06 ± 0.00 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.74 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 5b49226..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | pp512 | 787.74 ± 4.26 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | tg128 | 8.48 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 288c978..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 57.56 ± 0.00 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.74 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index a2a39be..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | pp512 | 779.79 ± 2.46 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | tg128 | 8.49 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 6bf5a79..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 86.41 ± 0.00 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 5.56 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index b0b79dd..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | pp512 | 793.84 ± 5.06 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | 0 | tg128 | 8.49 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index c9d928f..0000000 --- a/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 85.44 ± 0.00 | -| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 5.55 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 55588ef..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | pp512 | 1047.96 ± 3.88 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | tg128 | 41.16 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index d1d0f6b..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 812.61 ± 0.00 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 36.43 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 7cf3ee3..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | pp512 | 1028.24 ± 6.22 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | tg128 | 41.14 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 0e862a7..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 811.19 ± 0.00 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 36.40 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 60b0e11..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | pp512 | 565.30 ± 3.35 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | tg128 | 41.68 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 82cb701..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 632.28 ± 0.00 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 34.85 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index c5502bf..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | pp512 | 557.83 ± 3.26 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | tg128 | 41.65 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index a477cfc..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 633.59 ± 0.00 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 34.87 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 72a07ab..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | pp512 | 1054.77 ± 4.94 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | tg128 | 41.44 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index eebc71a..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 671.89 ± 0.00 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 36.37 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 1d99572..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | pp512 | 1029.81 ± 2.15 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 1 | 0 | tg128 | 41.46 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 18edd08..0000000 --- a/benchmark/results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 674.11 ± 0.00 | -| nemotron_h_moe 31B.A3.5B Q8_0 | 37.66 GiB | 31.58 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 36.47 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 8dce1e8..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | pp512 | 202.60 ± 2.04 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 15.10 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 0ef8d8e..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 26.76 ± 0.00 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.08 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 186db12..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | pp512 | 200.59 ± 1.45 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 15.13 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index b37fb0f..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 26.64 ± 0.00 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.07 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index b01b440..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | pp512 | 201.43 ± 2.43 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 16.10 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 95e68d3..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,19 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 29.54 ± 0.00 | -/opt/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:96: ROCm error -:0:rocdevice.cpp :3618: 63153010732 us: Callback: Queue 0x7f3225300000 aborting with error : HSA_STATUS_ERROR_MEMORY_APERTURE_VIOLATION: The agent attempted to access memory beyond the largest legal address. code: 0x29 -/usr/local/lib64/libggml-base.so.0(+0x35a5) [0x7f3234ef25a5] -/usr/local/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7f3234ef296b] -/usr/local/lib64/libggml-base.so.0(ggml_abort+0x11f) [0x7f3234ef2aef] -/usr/local/lib64/libggml-hip.so.0(+0x2ca3912) [0x7f3237c52912] -/usr/local/lib64/libggml-hip.so.0(+0x2ca8cde) [0x7f3237c57cde] -/usr/local/lib64/libggml-base.so.0(ggml_backend_sched_synchronize+0x2e) [0x7f3234f09e5e] -/usr/local/lib64/libllama.so.0(_ZN13llama_context11synchronizeEv+0x10) [0x7f3238331630] -/usr/local/bin/llama-bench() [0x408ca6] -/lib64/libc.so.6(+0x35b5) [0x7f32348885b5] -/lib64/libc.so.6(__libc_start_main+0x88) [0x7f3234888668] -/usr/local/bin/llama-bench() [0x409cf5] -✖ ! [rocm-7alpha-rocwmma] Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__fa1 __longctx32768 failed (exit 0) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index e31184b..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | pp512 | 201.86 ± 2.71 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 16.13 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index afed40a..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 29.34 ± 0.00 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 2.03 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index d5f5df3..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | pp512 | 193.57 ± 10.23 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 14.83 ± 0.53 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 7ecc21d..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 33.05 ± 0.00 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 2.90 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 95ab277..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | pp512 | 199.80 ± 0.99 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 15.14 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 51c1f95..0000000 --- a/benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 33.25 ± 0.00 | -| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 2.90 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 82f3de7..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 565.84 ± 2.23 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 26.86 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index d39f419..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 118.25 ± 0.00 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 12.61 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 12a6821..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 572.78 ± 6.78 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 26.81 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index d0f4200..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 123.38 ± 0.00 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 12.43 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 6af7459..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 488.98 ± 3.11 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 27.10 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 717da60..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 136.27 ± 0.00 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 7.47 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 25320db..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 490.86 ± 3.57 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 27.11 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index cc98b6f..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 131.40 ± 0.00 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 7.48 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 9d5b902..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 466.91 ± 3.25 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 27.10 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 1bb542a..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 129.72 ± 0.00 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 13.50 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 9e54070..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 467.48 ± 2.87 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 27.09 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 3c96eaa..0000000 --- a/benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 126.75 ± 0.00 | -| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 13.51 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 8054c25..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 1062.68 ± 4.46 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 57.77 ± 0.02 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index c57b797..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 127.28 ± 0.00 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 16.99 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 83d5ea8..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 1056.43 ± 9.46 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 58.04 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 7990d4b..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 128.77 ± 0.00 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 16.98 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index e2beb13..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 912.93 ± 3.31 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 58.61 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 87f3d6b..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 142.02 ± 0.00 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 8.77 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 26f6ef8..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 918.79 ± 3.83 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 58.60 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index e78f3ec..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 141.82 ± 0.00 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 8.79 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 2a098a4..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 982.10 ± 4.60 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 57.77 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index cedf966..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 138.54 ± 0.00 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 18.30 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 895e2f4..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 984.86 ± 9.16 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 57.90 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 717b9c2..0000000 --- a/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 138.98 ± 0.00 | -| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 18.33 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 117e5b9..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 1230.43 ± 11.07 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 68.83 ± 0.03 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 8bf99af..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 129.18 ± 0.00 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 17.59 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 9a0c06d..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 1225.92 ± 10.08 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 68.92 ± 0.02 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 17ac854..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 128.45 ± 0.00 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 17.59 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 029696b..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 1219.57 ± 14.84 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 71.70 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 8dd2c6f..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 146.44 ± 0.00 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 8.97 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 72d9ba5..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 1220.24 ± 11.95 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 71.58 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 03fc6e4..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 140.58 ± 0.00 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 8.96 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index c4c1485..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 1199.99 ± 6.19 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 69.44 ± 0.03 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 221f492..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 140.63 ± 0.00 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 19.09 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index ca9ecdb..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | pp512 | 1197.52 ± 8.13 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 69.22 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 8ad658a..0000000 --- a/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 140.70 ± 0.00 | -| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 19.10 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 18ab4a2..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | pp512 | 589.90 ± 6.32 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | tg128 | 28.16 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index b19fe6c..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 373.61 ± 0.00 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 22.27 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index e524579..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | pp512 | 605.45 ± 4.55 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | tg128 | 28.11 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 8f19370..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 380.23 ± 0.00 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 22.22 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 5b99ce5..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | pp512 | 353.61 ± 9.32 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | tg128 | 29.26 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index ae39d24..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 282.62 ± 0.00 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 22.83 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index b11f674..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | pp512 | 367.06 ± 4.12 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | tg128 | 29.31 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 78853fc..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 290.72 ± 0.00 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 22.86 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index db0fffb..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | pp512 | 586.46 ± 4.62 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | tg128 | 28.73 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 233d69f..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 353.48 ± 0.00 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 22.51 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 2da1661..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | pp512 | 602.30 ± 1.01 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 1 | 0 | tg128 | 28.74 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 4b787ab..0000000 --- a/benchmark/results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 358.54 ± 0.00 | -| qwen3next 80B.A3B Q8_0 | 79.57 GiB | 79.67 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 22.53 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index d8becac..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | pp512 | 915.98 ± 0.27 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.15 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 0c21b83..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 144.17 ± 0.00 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 10.21 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 066ece9..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | pp512 | 918.69 ± 0.81 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.15 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index e5091cf..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 142.71 ± 0.00 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 10.24 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 0197948..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | pp512 | 422.39 ± 1.28 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.16 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 4372985..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 267.47 ± 0.00 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 10.05 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 7164345..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | pp512 | 423.79 ± 0.33 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.17 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 87784fa..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 263.80 ± 0.00 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 10.09 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 4a12b25..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | pp512 | 897.91 ± 0.80 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.17 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 4b015ca..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 155.37 ± 0.00 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 10.22 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 03e0298..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | pp512 | 905.67 ± 0.84 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.15 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 1ffe911..0000000 --- a/benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 171.87 ± 0.00 | -| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 10.26 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index eff348c..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | pp512 | 468.64 ± 0.38 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | tg128 | 4.00 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index f3529f1..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 88.82 ± 0.00 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.43 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index d5910d6..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | pp512 | 525.72 ± 0.44 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | tg128 | 4.00 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index e778d5d..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 93.45 ± 0.00 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.43 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 570fa39..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,2 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 92cea90..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 92.58 ± 0.00 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.12 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index cc84ef4..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | pp512 | 523.92 ± 1.74 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | tg128 | 4.01 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 1163ff1..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 92.90 ± 0.00 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.12 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index e291950..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | pp512 | 464.70 ± 1.33 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | tg128 | 4.03 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index c8b651c..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 127.77 ± 0.00 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.48 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 94990ff..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | pp512 | 523.70 ± 0.88 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | tg128 | 4.03 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 5cc9f6c..0000000 --- a/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 125.47 ± 0.00 | -| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 3.49 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 4bef89e..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | pp512 | 2881.51 ± 4.15 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 77.27 ± 2.44 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 92e5c0e..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 849.40 ± 0.00 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 58.01 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index ffcbaeb..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | pp512 | 2891.26 ± 1.42 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 78.55 ± 0.02 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 43d80f5..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 852.79 ± 0.00 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 58.11 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 4e0ac20..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | pp512 | 2794.32 ± 20.28 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 81.04 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 5408a7d..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 1196.36 ± 0.00 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 59.62 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 9c3ec2b..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | pp512 | 2690.59 ± 197.24 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 68.41 ± 4.26 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 376a993..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 1205.66 ± 0.00 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 59.64 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 10dfe8b..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | pp512 | 2811.05 ± 10.85 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 78.49 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index bbe1dee..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 1063.31 ± 0.00 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 58.08 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 52eaf34..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | pp512 | 2812.26 ± 11.64 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 70.74 ± 8.86 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 8d6d07b..0000000 --- a/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 1064.82 ± 0.00 | -| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 58.06 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 408fa56..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | pp512 | 687.06 ± 8.06 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | tg128 | 51.55 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 6d41aef..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 307.43 ± 0.00 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 19.89 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index aed7951..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | pp512 | 687.03 ± 1.93 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | tg128 | 51.68 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 67d8d83..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 307.27 ± 0.00 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 19.89 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index dd7eee3..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | pp512 | 278.28 ± 5.27 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | tg128 | 51.90 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 60200b7..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 190.34 ± 0.00 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 19.96 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index ae1f87b..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | pp512 | 285.78 ± 0.23 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | tg128 | 51.91 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 688c546..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 191.59 ± 0.00 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 19.94 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 61d9850..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | pp512 | 677.02 ± 4.35 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | tg128 | 51.80 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index f57e1b5..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 224.05 ± 0.00 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 19.92 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index b067646..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | pp512 | 693.01 ± 6.24 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | 0 | tg128 | 51.72 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index e426fc1..0000000 --- a/benchmark/results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 224.69 ± 0.00 | -| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 19.89 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index aaae77e..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 1796.98 ± 13.31 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 72.90 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 852e227..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 485.17 ± 0.00 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 29.14 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index 0f59a65..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 1788.91 ± 36.82 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 73.01 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 12b89e4..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 485.74 ± 0.00 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 29.08 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 6cc3e41..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 833.43 ± 3.27 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 73.20 ± 0.03 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 1557cf0..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 314.25 ± 0.00 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 29.21 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index 56acd7b..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 822.67 ± 8.71 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 73.17 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 30ff8b0..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 313.82 ± 0.00 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 29.19 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 466c31f..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 1779.00 ± 10.42 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 73.22 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index f2eebb9..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 349.09 ± 0.00 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 29.12 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 485665b..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 1775.23 ± 21.22 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 73.12 ± 0.02 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 1b5c671..0000000 --- a/benchmark/results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 349.31 ± 0.00 | -| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 29.14 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1.log b/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1.log deleted file mode 100644 index 002583a..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | pp512 | 1578.53 ± 1.91 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | tg128 | 51.01 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1__longctx32768.log b/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1__longctx32768.log deleted file mode 100644 index 930e31b..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 47.34 ± 0.00 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 6.93 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1.log b/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1.log deleted file mode 100644 index dc678a1..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | pp512 | 1583.99 ± 4.22 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | tg128 | 51.06 ± 0.02 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index 957c992..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 49.27 ± 0.00 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 6.93 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1.log b/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1.log deleted file mode 100644 index 78fccc0..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | pp512 | 671.29 ± 0.53 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | tg128 | 50.59 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1__longctx32768.log b/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1__longctx32768.log deleted file mode 100644 index eb8fe9b..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 43.39 ± 0.00 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 5.59 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1.log b/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1.log deleted file mode 100644 index af3f138..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | pp512 | 670.47 ± 0.30 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | tg128 | 50.61 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index e77433c..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 42.56 ± 0.00 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 5.59 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1.log b/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1.log deleted file mode 100644 index 06aedd2..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | pp512 | 1547.50 ± 0.77 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | tg128 | 50.90 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1__longctx32768.log b/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1__longctx32768.log deleted file mode 100644 index f221dd4..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 84.83 ± 0.00 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 7.79 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1.log b/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1.log deleted file mode 100644 index 6d91a31..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | pp512 | 1543.82 ± 2.88 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | tg128 | 50.92 ± 0.01 | - -build: 9c142e3a2 (7670) diff --git a/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log b/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log deleted file mode 100644 index aac41ae..0000000 --- a/benchmark/results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log +++ /dev/null @@ -1,8 +0,0 @@ -ggml_cuda_init: found 1 ROCm devices: - Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 -| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s | -| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 83.93 ± 0.00 | -| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 7.79 ± 0.00 | - -build: 9c142e3a2 (7670) diff --git a/docs/results.json b/docs/results.json index 4318157..c8c6275 100644 --- a/docs/results.json +++ b/docs/results.json @@ -1,6 +1,6 @@ { "meta": { - "generated_at": "2026-01-11T10:01:18Z", + "generated_at": "2026-01-12T09:25:21Z", "system_info": { "distro": "Fedora Linux 42 (Workstation Edition)", "kernel": "6.18.3-100.fc42.x86_64", @@ -16,16 +16,10 @@ "environments": [ "rocm6_4_4", "rocm6_4_4-hblt0", - "rocm6_4_4-rocwmma", - "rocm6_4_4-rocwmma-hblt0", "rocm7-nightlies", "rocm7-nightlies-hblt0", - "rocm7-nightlies-rocwmma", - "rocm7-nightlies-rocwmma-hblt0", "rocm7.1.1", "rocm7.1.1-hblt0", - "rocm7.1.1-rocwmma", - "rocm7.1.1-rocwmma-hblt0", "rocm7_rc", "vulkan_amdvlk", "vulkan_radv" @@ -33,230 +27,6 @@ "notes": "pp512 = prompt processing; tg128 = text generation; t/s = tokens/second" }, "runs": [ - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 80.08, - "tps_std": 0.03, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.7, - "tps_std": 0.14, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 6.9, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 0.72, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 78.81, - "tps_std": 0.04, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.71, - "tps_std": 0.13, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 6.9, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 0.72, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", @@ -481,230 +251,6 @@ "number": "7670" } }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 73.15, - "tps_std": 0.02, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.81, - "tps_std": 0.14, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 7.28, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 0.61, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 73.91, - "tps_std": 0.04, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.75, - "tps_std": 0.21, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 7.24, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 0.61, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", @@ -898,230 +444,6 @@ "number": "7670" } }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 79.77, - "tps_std": 0.04, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.86, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 9.04, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 0.68, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 78.6, - "tps_std": 0.02, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.83, - "tps_std": 0.03, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 9.06, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", - "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 0.68, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 125.03, - "file_size_gib": 70.31, - "name_params_b": 125.03, - "quant": "Q4_K_XL", - "log": "results/Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL-00001-of-00002", "model_clean": "Devstral-2-123B-Instruct-2512-UD-Q4_K_XL", @@ -1570,230 +892,6 @@ "number": "7670" } }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 275.09, - "tps_std": 0.35, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 21.72, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 13.65, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.7, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 303.19, - "tps_std": 1.3, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 21.71, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 13.9, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.7, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", @@ -2018,199 +1116,6 @@ "number": "7670" } }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 188.28, - "tps_std": 0.38, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 22.62, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 14.5, - "tps_std": 0.0, - "error": true, - "error_type": "runtime", - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": null - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 234.18, - "tps_std": 1.9, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 22.63, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 14.74, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.38, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", @@ -2435,230 +1340,6 @@ "number": "7670" } }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 273.31, - "tps_std": 0.52, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 21.7, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 18.48, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.58, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 299.53, - "tps_std": 0.59, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 21.68, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 18.59, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", - "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.58, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 68.01, - "name_params_b": 110.47, - "quant": "Q4_K_XL", - "log": "results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002", "model_clean": "GLM-4.5-Air-UD-Q4_K_XL", @@ -3107,230 +1788,6 @@ "number": "7670" } }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 150.46, - "tps_std": 0.44, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 16.55, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 12.78, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.66, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 193.25, - "tps_std": 0.21, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 16.55, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 13.69, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.66, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", @@ -3555,230 +2012,6 @@ "number": "7670" } }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 88.49, - "tps_std": 0.23, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 16.65, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 13.47, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.34, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 152.24, - "tps_std": 0.6, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 16.63, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 14.35, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.34, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", @@ -4003,230 +2236,6 @@ "number": "7670" } }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 145.3, - "tps_std": 0.23, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 16.51, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 17.44, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.54, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 185.77, - "tps_std": 0.97, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 16.5, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 18.15, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", - "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.55, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 110.47, - "file_size_gib": 94.57, - "name_params_b": 110.47, - "quant": "Q6_K_XL", - "log": "results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003", "model_clean": "GLM-4.5-Air-UD-Q6_K_XL", @@ -4675,230 +2684,6 @@ "number": "7670" } }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 147.48, - "tps_std": 0.05, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.78, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 11.84, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.08, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 145.63, - "tps_std": 0.1, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.78, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 11.77, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.07, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", @@ -5123,230 +2908,6 @@ "number": "7670" } }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 67.04, - "tps_std": 0.02, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.79, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 11.46, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 0.8, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 66.63, - "tps_std": 0.03, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.79, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 11.47, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 0.8, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", @@ -5571,230 +3132,6 @@ "number": "7670" } }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 146.76, - "tps_std": 0.06, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.79, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 16.13, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.06, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 145.07, - "tps_std": 0.15, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 2.79, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 16.14, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 1.06, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 70.55, - "file_size_gib": 75.65, - "name_params_b": 70.55, - "quant": "Q8_K_XL", - "log": "results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002", "model_clean": "Llama-3.3-70B-Instruct-UD-Q8_K_XL", @@ -6243,230 +3580,6 @@ "number": "7670" } }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 792.51, - "tps_std": 3.25, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 8.47, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 54.31, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 5.48, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 794.81, - "tps_std": 3.31, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 8.47, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 53.85, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 5.49, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Ministral-3-14B-Instruct-2512-BF16", "model_clean": "Ministral-3-14B-Instruct-2512-BF16", @@ -6691,230 +3804,6 @@ "number": "7670" } }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 789.37, - "tps_std": 1.53, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 8.48, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 58.06, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.74, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 787.74, - "tps_std": 4.26, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 8.48, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 57.56, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.74, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Ministral-3-14B-Instruct-2512-BF16", "model_clean": "Ministral-3-14B-Instruct-2512-BF16", @@ -7139,230 +4028,6 @@ "number": "7670" } }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 779.79, - "tps_std": 2.46, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 8.49, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 86.41, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 5.56, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 793.84, - "tps_std": 5.06, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 8.49, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 85.44, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Ministral-3-14B-Instruct-2512-BF16", - "model_clean": "Ministral-3-14B-Instruct-2512-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 5.55, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 13.51, - "file_size_gib": 25.16, - "name_params_b": 13.51, - "quant": "BF16", - "log": "results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Ministral-3-14B-Instruct-2512-BF16", "model_clean": "Ministral-3-14B-Instruct-2512-BF16", @@ -7811,230 +4476,6 @@ "number": "7670" } }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1047.96, - "tps_std": 3.88, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 41.16, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 812.61, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 36.43, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1028.24, - "tps_std": 6.22, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 41.14, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 811.19, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 36.4, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", @@ -8259,230 +4700,6 @@ "number": "7670" } }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 565.3, - "tps_std": 3.35, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 41.68, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 632.28, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 34.85, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 557.83, - "tps_std": 3.26, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 41.65, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 633.59, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 34.87, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", @@ -8707,230 +4924,6 @@ "number": "7670" } }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1054.77, - "tps_std": 4.94, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 41.44, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 671.89, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 36.37, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1029.81, - "tps_std": 2.15, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 41.46, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 674.11, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 36.47, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 31.58, - "file_size_gib": 37.66, - "name_params_b": 31.58, - "quant": "Q8_K_XL", - "log": "results/Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", "model_clean": "Nemotron-3-Nano-30B-A3B-UD-Q8_K_XL", @@ -9379,230 +5372,6 @@ "number": "7670" } }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 202.6, - "tps_std": 2.04, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 15.1, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 26.76, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.08, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 200.59, - "tps_std": 1.45, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 15.13, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 26.64, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.07, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", @@ -9827,199 +5596,6 @@ "number": "7670" } }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 201.43, - "tps_std": 2.43, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 16.1, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 29.54, - "tps_std": 0.0, - "error": true, - "error_type": "runtime", - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": null - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 201.86, - "tps_std": 2.71, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 16.13, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 29.34, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 2.03, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", @@ -10244,230 +5820,6 @@ "number": "7670" } }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 193.57, - "tps_std": 10.23, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 14.83, - "tps_std": 0.53, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 33.05, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 2.9, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 199.8, - "tps_std": 0.99, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 15.14, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 33.25, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", - "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 2.9, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 235.09, - "file_size_gib": 96.99, - "name_params_b": 235.09, - "quant": "Q3_K_XL", - "log": "results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003", "model_clean": "Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL", @@ -10885,230 +6237,6 @@ "number": "7670" } }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 565.84, - "tps_std": 2.23, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 26.86, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 118.25, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 12.61, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 572.78, - "tps_std": 6.78, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 26.81, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 123.38, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 12.43, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-30B-A3B-BF16-00001-of-00002", "model_clean": "Qwen3-30B-A3B-BF16", @@ -11333,230 +6461,6 @@ "number": "7670" } }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 488.98, - "tps_std": 3.11, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 27.1, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 136.27, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 7.47, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 490.86, - "tps_std": 3.57, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 27.11, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 131.4, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 7.48, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-30B-A3B-BF16-00001-of-00002", "model_clean": "Qwen3-30B-A3B-BF16", @@ -11781,230 +6685,6 @@ "number": "7670" } }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 466.91, - "tps_std": 3.25, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 27.1, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 129.72, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 13.5, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 467.48, - "tps_std": 2.87, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 27.09, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 126.75, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-BF16-00001-of-00002", - "model_clean": "Qwen3-30B-A3B-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 13.51, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 56.89, - "name_params_b": 30.53, - "quant": "BF16", - "log": "results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-30B-A3B-BF16-00001-of-00002", "model_clean": "Qwen3-30B-A3B-BF16", @@ -12453,230 +7133,6 @@ "number": "7670" } }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1062.68, - "tps_std": 4.46, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 57.77, - "tps_std": 0.02, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 127.28, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 16.99, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1056.43, - "tps_std": 9.46, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 58.04, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 128.77, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 16.98, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", @@ -12901,230 +7357,6 @@ "number": "7670" } }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 912.93, - "tps_std": 3.31, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 58.61, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 142.02, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 8.77, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 918.79, - "tps_std": 3.83, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 58.6, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 141.82, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 8.79, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", @@ -13349,230 +7581,6 @@ "number": "7670" } }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 982.1, - "tps_std": 4.6, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 57.77, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 138.54, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 18.3, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 984.86, - "tps_std": 9.16, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 57.9, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 138.98, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 18.33, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 24.53, - "name_params_b": 30.53, - "quant": "Q6_K_XL", - "log": "results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", "model_clean": "Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL", @@ -14021,230 +8029,6 @@ "number": "7670" } }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1230.43, - "tps_std": 11.07, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 68.83, - "tps_std": 0.03, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 129.18, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 17.59, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1225.92, - "tps_std": 10.08, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 68.92, - "tps_std": 0.02, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 128.45, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 17.59, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", @@ -14469,230 +8253,6 @@ "number": "7670" } }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1219.57, - "tps_std": 14.84, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 71.7, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 146.44, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 8.97, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1220.24, - "tps_std": 11.95, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 71.58, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 140.58, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 8.96, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", @@ -14917,230 +8477,6 @@ "number": "7670" } }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1199.99, - "tps_std": 6.19, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 69.44, - "tps_std": 0.03, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 140.63, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 19.09, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1197.52, - "tps_std": 8.13, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 69.22, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 140.7, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 19.1, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 30.53, - "file_size_gib": 17.35, - "name_params_b": 30.53, - "quant": "Q4_K_M", - "log": "results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", "model_clean": "Qwen3-Coder-30B-A3B-Instruct-Q4_K_M", @@ -15589,230 +8925,6 @@ "number": "7670" } }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 589.9, - "tps_std": 6.32, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 28.16, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 373.61, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 22.27, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 605.45, - "tps_std": 4.55, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 28.11, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 380.23, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 22.22, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", @@ -16037,230 +9149,6 @@ "number": "7670" } }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 353.61, - "tps_std": 9.32, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 29.26, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 282.62, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 22.83, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 367.06, - "tps_std": 4.12, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 29.31, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 290.72, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 22.86, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", @@ -16485,230 +9373,6 @@ "number": "7670" } }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 586.46, - "tps_std": 4.62, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 28.73, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 353.48, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 22.51, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 602.3, - "tps_std": 1.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 28.74, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 358.54, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", - "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 22.53, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 79.67, - "file_size_gib": 79.57, - "name_params_b": 79.67, - "quant": "Q8_K_XL", - "log": "results/Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002", "model_clean": "Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL", @@ -17157,230 +9821,6 @@ "number": "7670" } }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 915.98, - "tps_std": 0.27, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 14.15, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 144.17, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 10.21, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 918.69, - "tps_std": 0.81, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 14.15, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 142.71, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 10.24, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gemma-3-12b-it-UD-Q8_K_XL", "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", @@ -17605,230 +10045,6 @@ "number": "7670" } }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 422.39, - "tps_std": 1.28, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 14.16, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 267.47, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 10.05, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 423.79, - "tps_std": 0.33, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 14.17, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 263.8, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 10.09, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gemma-3-12b-it-UD-Q8_K_XL", "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", @@ -18053,230 +10269,6 @@ "number": "7670" } }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 897.91, - "tps_std": 0.8, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 14.17, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 155.37, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 10.22, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 905.67, - "tps_std": 0.84, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 14.15, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 171.87, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-12b-it-UD-Q8_K_XL", - "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 10.26, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 11.77, - "file_size_gib": 13.4, - "name_params_b": 11.77, - "quant": "Q8_K_XL", - "log": "results/gemma-3-12b-it-UD-Q8_K_XL__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gemma-3-12b-it-UD-Q8_K_XL", "model_clean": "gemma-3-12b-it-UD-Q8_K_XL", @@ -18725,230 +10717,6 @@ "number": "7670" } }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 468.64, - "tps_std": 0.38, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 4.0, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 88.82, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.43, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 525.72, - "tps_std": 0.44, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 4.0, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 93.45, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.43, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gemma-3-27b-it-BF16-00001-of-00002", "model_clean": "gemma-3-27b-it-BF16", @@ -19173,199 +10941,6 @@ "number": "7670" } }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": null, - "tps_mean": null, - "tps_std": null, - "error": false, - "error_type": null, - "backend": null, - "ngl": null, - "mmap": null, - "params_b": null, - "file_size_gib": null, - "name_params_b": null, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": null - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 92.58, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.12, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 523.92, - "tps_std": 1.74, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 4.01, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 92.9, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.12, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gemma-3-27b-it-BF16-00001-of-00002", "model_clean": "gemma-3-27b-it-BF16", @@ -19590,230 +11165,6 @@ "number": "7670" } }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 464.7, - "tps_std": 1.33, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 4.03, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 127.77, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.48, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 523.7, - "tps_std": 0.88, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 4.03, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 125.47, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-27b-it-BF16-00001-of-00002", - "model_clean": "gemma-3-27b-it-BF16", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 3.49, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 27.01, - "file_size_gib": 50.31, - "name_params_b": 27.01, - "quant": "BF16", - "log": "results/gemma-3-27b-it-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gemma-3-27b-it-BF16-00001-of-00002", "model_clean": "gemma-3-27b-it-BF16", @@ -20287,230 +11638,6 @@ "number": "7670" } }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 2881.51, - "tps_std": 4.15, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 77.27, - "tps_std": 2.44, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 849.4, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 58.01, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 2891.26, - "tps_std": 1.42, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 78.55, - "tps_std": 0.02, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 852.79, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 58.11, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gemma-3-4b-it-Q3_K_S", "model_clean": "gemma-3-4b-it-Q3_K_S", @@ -20735,230 +11862,6 @@ "number": "7670" } }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 2794.32, - "tps_std": 20.28, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 81.04, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 1196.36, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 59.62, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 2690.59, - "tps_std": 197.24, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 68.41, - "tps_std": 4.26, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 1205.66, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 59.64, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gemma-3-4b-it-Q3_K_S", "model_clean": "gemma-3-4b-it-Q3_K_S", @@ -21183,230 +12086,6 @@ "number": "7670" } }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 2811.05, - "tps_std": 10.85, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 78.49, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 1063.31, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 58.08, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 2812.26, - "tps_std": 11.64, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 70.74, - "tps_std": 8.86, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 1064.82, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gemma-3-4b-it-Q3_K_S", - "model_clean": "gemma-3-4b-it-Q3_K_S", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 58.06, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 3.88, - "file_size_gib": 1.8, - "name_params_b": 3.88, - "quant": "Q3_K_S", - "log": "results/gemma-3-4b-it-Q3_K_S__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gemma-3-4b-it-Q3_K_S", "model_clean": "gemma-3-4b-it-Q3_K_S", @@ -21855,230 +12534,6 @@ "number": "7670" } }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 687.06, - "tps_std": 8.06, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 51.55, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 307.43, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 19.89, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 687.03, - "tps_std": 1.93, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 51.68, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 307.27, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 19.89, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gpt-oss-120b-mxfp4-00001-of-00003", "model_clean": "gpt-oss-120b-mxfp4", @@ -22303,230 +12758,6 @@ "number": "7670" } }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 278.28, - "tps_std": 5.27, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 51.9, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 190.34, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 19.96, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 285.78, - "tps_std": 0.23, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 51.91, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 191.59, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 19.94, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gpt-oss-120b-mxfp4-00001-of-00003", "model_clean": "gpt-oss-120b-mxfp4", @@ -22751,230 +12982,6 @@ "number": "7670" } }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 677.02, - "tps_std": 4.35, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 51.8, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 224.05, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 19.92, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 693.01, - "tps_std": 6.24, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 51.72, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 224.69, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-120b-mxfp4-00001-of-00003", - "model_clean": "gpt-oss-120b-mxfp4", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 19.89, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 116.83, - "file_size_gib": 59.02, - "name_params_b": 116.83, - "quant": "MXFP4", - "log": "results/gpt-oss-120b-mxfp4-00001-of-00003__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gpt-oss-120b-mxfp4-00001-of-00003", "model_clean": "gpt-oss-120b-mxfp4", @@ -23423,230 +13430,6 @@ "number": "7670" } }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1796.98, - "tps_std": 13.31, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 72.9, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 485.17, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 29.14, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1788.91, - "tps_std": 36.82, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 73.01, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 485.74, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 29.08, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gpt-oss-20b-mxfp4", "model_clean": "gpt-oss-20b-mxfp4", @@ -23871,230 +13654,6 @@ "number": "7670" } }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 833.43, - "tps_std": 3.27, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 73.2, - "tps_std": 0.03, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 314.25, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 29.21, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 822.67, - "tps_std": 8.71, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 73.17, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 313.82, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 29.19, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gpt-oss-20b-mxfp4", "model_clean": "gpt-oss-20b-mxfp4", @@ -24319,230 +13878,6 @@ "number": "7670" } }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1779.0, - "tps_std": 10.42, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 73.22, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 349.09, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 29.12, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1775.23, - "tps_std": 21.22, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 73.12, - "tps_std": 0.02, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 349.31, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "gpt-oss-20b-mxfp4", - "model_clean": "gpt-oss-20b-mxfp4", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 29.14, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 20.91, - "file_size_gib": 11.27, - "name_params_b": 20.91, - "quant": "MXFP4", - "log": "results/gpt-oss-20b-mxfp4__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "gpt-oss-20b-mxfp4", "model_clean": "gpt-oss-20b-mxfp4", @@ -24991,230 +14326,6 @@ "number": "7670" } }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1578.53, - "tps_std": 1.91, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 51.01, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 47.34, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm6_4_4-rocwmma", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 6.93, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1583.99, - "tps_std": 4.22, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 51.06, - "tps_std": 0.02, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 49.27, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm6_4_4-rocwmma-hblt0", - "env_base": "rocm6_4_4", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 6.93, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "llama-2-7b.Q4_0", "model_clean": "llama-2-7b.Q4_0", @@ -25439,230 +14550,6 @@ "number": "7670" } }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 671.29, - "tps_std": 0.53, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 50.59, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 43.39, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7-nightlies-rocwmma", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 5.59, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 670.47, - "tps_std": 0.3, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 50.61, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 42.56, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7-nightlies-rocwmma-hblt0", - "env_base": "rocm7", - "env_variant": "nightlies-rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 5.59, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7-nightlies-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "llama-2-7b.Q4_0", "model_clean": "llama-2-7b.Q4_0", @@ -25887,230 +14774,6 @@ "number": "7670" } }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1547.5, - "tps_std": 0.77, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 50.9, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 84.83, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7.1.1-rocwmma", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 7.79, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "pp512", - "tps_mean": 1543.82, - "tps_std": 2.88, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "default", - "context_tokens": null, - "test": "tg128", - "tps_mean": 50.92, - "tps_std": 0.01, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "pp2048 @ d32768", - "tps_mean": 83.93, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, - { - "model": "llama-2-7b.Q4_0", - "model_clean": "llama-2-7b.Q4_0", - "env": "rocm7.1.1-rocwmma-hblt0", - "env_base": "rocm7.1.1", - "env_variant": "rocwmma-hblt0", - "fa": true, - "context": "longctx32768", - "context_tokens": 32768, - "test": "tg32 @ d32768", - "tps_mean": 7.79, - "tps_std": 0.0, - "error": false, - "error_type": null, - "backend": "ROCm", - "ngl": 99, - "mmap": 0, - "params_b": 6.74, - "file_size_gib": 3.56, - "name_params_b": 6.74, - "quant": "Q4_0", - "log": "results/llama-2-7b.Q4_0__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768.log", - "rpc": false, - "build": { - "hash": "9c142e3a2", - "number": "7670" - } - }, { "model": "llama-2-7b.Q4_0", "model_clean": "llama-2-7b.Q4_0",