julian/amd-strix-halo-toolboxes
1
0
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Updated benchmarkls with ROCm 6.4.4

Browse Source
This commit is contained in:
Donato Capitella
2025-09-28 09:38:04 +01:00
parent 7dd4490398
commit ba88675b9c
142 changed files with 8449 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/generate_markdown_results.py
+15 -15
View File
@@ -23,11 +23,11 @@ ENV_LABEL: Dict[str, str] = {
"rocm7_rc-hblt0": "ROCm 7 RC (hipBLASLt OFF)",
"rocm7_rc-rocwmma-hblt0": "ROCm 7 RC + ROCWMMA (hipBLASLt OFF)",
# ROCm 6.4.3
"rocm6_4_3": "ROCm 6.4.3 (hipBLASLt)",
"rocm6_4_3-hblt0": "ROCm 6.4.3 (hipBLASLt OFF)",
"rocm6_4_3-rocwmma": "ROCm 6.4.3 + ROCWMMA (hipBLASLt)",
"rocm6_4_3-rocwmma-hblt0": "ROCm 6.4.3 + ROCWMMA (hipBLASLt OFF)",
# ROCm 6.4.4
"rocm6_4_4": "ROCm 6.4.4 (hipBLASLt)",
"rocm6_4_4-hblt0": "ROCm 6.4.4 (hipBLASLt OFF)",
"rocm6_4_4-rocwmma": "ROCm 6.4.4 + ROCWMMA (hipBLASLt)",
"rocm6_4_4-rocwmma-hblt0": "ROCm 6.4.4 + ROCWMMA (hipBLASLt OFF)",
# Vulkan
"vulkan_amdvlk": "Vulkan AMDVLK",
@@ -461,17 +461,17 @@ def build_benchmarks_doc(
lines.append(md_row([ENV_LABEL.get(env, env), fmt_eff(row_pp), fmt_eff(row_tg)]))
lines.append("")
# ROCWMMA effect — check both ROCm 7 and 6.4.3 families if present
# ROCWMMA effect — check both ROCm 7 and 6.4.4 families if present
lines.append("### Impact of ROCWMMA")
rocwmma_pairs = []
if "rocm7_rc-rocwmma" in envs and "rocm7_rc" in envs:
rocwmma_pairs.append(("rocm7_rc-rocwmma", "rocm7_rc", "ROCm 7 RC (hipBLASLt)"))
if "rocm7_rc-rocwmma-hblt0" in envs and "rocm7_rc-hblt0" in envs:
rocwmma_pairs.append(("rocm7_rc-rocwmma-hblt0", "rocm7_rc-hblt0", "ROCm 7 RC (hipBLASLt OFF)"))
if "rocm6_4_3-rocwmma" in envs and "rocm6_4_3" in envs:
rocwmma_pairs.append(("rocm6_4_3-rocwmma", "rocm6_4_3", "ROCm 6.4.3 (hipBLASLt)"))
if "rocm6_4_3-rocwmma-hblt0" in envs and "rocm6_4_3-hblt0" in envs:
rocwmma_pairs.append(("rocm6_4_3-rocwmma-hblt0", "rocm6_4_3-hblt0", "ROCm 6.4.3 (hipBLASLt OFF)"))
if "rocm6_4_4-rocwmma" in envs and "rocm6_4_4" in envs:
rocwmma_pairs.append(("rocm6_4_4-rocwmma", "rocm6_4_4", "ROCm 6.4.4 (hipBLASLt)"))
if "rocm6_4_4-rocwmma-hblt0" in envs and "rocm6_4_4-hblt0" in envs:
rocwmma_pairs.append(("rocm6_4_4-rocwmma-hblt0", "rocm6_4_4-hblt0", "ROCm 6.4.4 (hipBLASLt OFF)"))
rocwmma_rows = rocwmma_effect(runs, rocwmma_pairs, TESTS)
lines.append(md_row(["Context", "Test", "Compared Envs", "Pairs", "Median Δ%"]))
@@ -480,17 +480,17 @@ def build_benchmarks_doc(
lines.append(md_row([label, test, f"{ENV_LABEL.get(env_on, env_on)} vs {ENV_LABEL.get(env_off, env_off)}", str(n), f"{delta}%"]))
lines.append("")
# hipBLASLt effect — for both ROCm 7 and 6.4.3 families
# hipBLASLt effect — for both ROCm 7 and 6.4.4 families
lines.append("### Impact of hipBLASLt")
hip_pairs = []
if "rocm7_rc" in envs and "rocm7_rc-hblt0" in envs:
hip_pairs.append(("rocm7_rc", "rocm7_rc-hblt0", "ROCm 7 RC (no ROCWMMA)"))
if "rocm7_rc-rocwmma" in envs and "rocm7_rc-rocwmma-hblt0" in envs:
hip_pairs.append(("rocm7_rc-rocwmma", "rocm7_rc-rocwmma-hblt0", "ROCm 7 RC + ROCWMMA"))
if "rocm6_4_3" in envs and "rocm6_4_3-hblt0" in envs:
hip_pairs.append(("rocm6_4_3", "rocm6_4_3-hblt0", "ROCm 6.4.3 (no ROCWMMA)"))
if "rocm6_4_3-rocwmma" in envs and "rocm6_4_3-rocwmma-hblt0" in envs:
hip_pairs.append(("rocm6_4_3-rocwmma", "rocm6_4_3-rocwmma-hblt0", "ROCm 6.4.3 + ROCWMMA"))
if "rocm6_4_4" in envs and "rocm6_4_4-hblt0" in envs:
hip_pairs.append(("rocm6_4_4", "rocm6_4_4-hblt0", "ROCm 6.4.4 (no ROCWMMA)"))
if "rocm6_4_4-rocwmma" in envs and "rocm6_4_4-rocwmma-hblt0" in envs:
hip_pairs.append(("rocm6_4_4-rocwmma", "rocm6_4_4-rocwmma-hblt0", "ROCm 6.4.4 + ROCWMMA"))
hip_rows = hipblaslt_effect(runs, hip_pairs, TESTS)
lines.append(md_row(["Context", "Test", "Compared Envs", "Pairs", "Median Δ%"]))
benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 0 | pp512 | 128.18 ± 0.37 |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 20.51 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 134.92 ± 0.21 |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.08 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 0 | pp512 | 159.31 ± 0.83 |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 20.34 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 171.67 ± 0.36 |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.04 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 0 | pp512 | 128.02 ± 0.30 |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 20.53 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 136.15 ± 0.32 |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.05 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 0 | pp512 | 160.41 ± 0.61 |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 20.50 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 161.32 ± 0.19 |
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.06 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | pp512 | 123.24 ± 0.42 |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 15.84 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 129.37 ± 0.24 |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.17 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | pp512 | 151.03 ± 0.45 |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 15.79 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 155.49 ± 0.74 |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.18 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | pp512 | 122.48 ± 0.34 |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 15.86 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 130.06 ± 0.38 |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.18 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | pp512 | 150.67 ± 0.75 |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 0 | tg128 | 15.84 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/GLM-4.5-Air-UD-Q6_K_XL-00001-of-00003__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 149.93 ± 0.58 |
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.18 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
hipBLASLt error: Heuristic Fetch Failed!
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 0 | pp512 | 98.87 ± 0.18 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 0 | tg128 | 2.77 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 104.31 ± 0.07 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 0 | pp512 | 97.43 ± 0.23 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 0 | tg128 | 2.76 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 103.81 ± 0.09 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.78 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
hipBLASLt error: Heuristic Fetch Failed!
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 0 | pp512 | 99.32 ± 0.17 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 0 | tg128 | 2.78 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 104.93 ± 0.11 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 0 | pp512 | 98.99 ± 0.21 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 0 | tg128 | 2.78 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 103.03 ± 0.23 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 276.88 ± 1.57 |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 14.66 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 292.47 ± 1.18 |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.83 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 277.79 ± 0.94 |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 14.65 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 292.17 ± 1.61 |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.83 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 276.97 ± 1.15 |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 14.71 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 293.79 ± 2.33 |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.84 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 278.59 ± 1.22 |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 14.70 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 296.61 ± 0.98 |
| llama4 17Bx16E (Scout) Q6_K | 82.35 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.83 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 281.33 ± 2.60 |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 11.89 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 297.14 ± 1.58 |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 12.00 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 280.36 ± 0.42 |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 11.88 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 298.12 ± 2.72 |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 12.00 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 279.89 ± 0.66 |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 11.92 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 297.68 ± 2.90 |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 11.97 ± 0.09 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 284.44 ± 3.25 |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 11.90 ± 0.04 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 300.04 ± 1.45 |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 12.00 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
hipBLASLt error: Heuristic Fetch Failed!
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 291.19 ± 2.35 |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 17.82 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 307.71 ± 1.77 |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 18.00 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 291.96 ± 2.18 |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 17.82 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 310.84 ± 1.35 |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 18.01 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
hipBLASLt error: Heuristic Fetch Failed!
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 291.26 ± 0.79 |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 17.83 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 311.26 ± 1.06 |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 17.97 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 290.78 ± 1.38 |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 17.81 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 1 | 0 | pp512 | 310.36 ± 1.62 |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 99 | 1 | 0 | tg128 | 18.00 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 0 | pp512 | 134.57 ± 0.66 |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 0 | tg128 | 14.57 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 144.38 ± 0.73 |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 14.90 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 0 | pp512 | 134.69 ± 1.05 |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 0 | tg128 | 14.58 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 143.45 ± 0.41 |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 14.97 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 0 | pp512 | 133.50 ± 0.67 |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 0 | tg128 | 14.55 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 144.31 ± 0.58 |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 14.93 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 0 | pp512 | 133.54 ± 0.74 |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 0 | tg128 | 14.54 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-00001-of-00003__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 144.26 ± 0.29 |
| qwen3moe 235B.A22B Q3_K - Medium | 96.99 GiB | 235.09 B | ROCm | 99 | 1 | 0 | tg128 | 14.92 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
hipBLASLt error: Heuristic Fetch Failed!
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 451.60 ± 1.80 |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 25.54 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 482.09 ± 5.55 |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 25.77 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 345.46 ± 3.07 |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 25.49 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 354.93 ± 5.65 |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 25.80 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
hipBLASLt error: Heuristic Fetch Failed!
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 448.97 ± 7.97 |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 25.57 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 489.49 ± 3.92 |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 25.78 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 343.78 ± 1.91 |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 25.48 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-BF16-00001-of-00002__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 363.09 ± 8.05 |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 25.75 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 577.98 ± 6.34 |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 55.37 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 623.53 ± 3.70 |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 56.76 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 582.34 ± 4.27 |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 55.34 ± 0.02 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 622.32 ± 5.83 |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 56.82 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 582.99 ± 4.97 |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 55.33 ± 0.02 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 632.12 ± 3.63 |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 56.73 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 0 | pp512 | 582.14 ± 4.21 |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 0 | tg128 | 55.39 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 632.63 ± 4.35 |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 1 | 0 | tg128 | 56.77 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 0 | pp512 | 754.71 ± 0.79 |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 0 | tg128 | 14.16 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 803.95 ± 0.73 |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.07 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 0 | pp512 | 768.26 ± 1.35 |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 0 | tg128 | 14.15 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 814.89 ± 0.73 |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.08 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 0 | pp512 | 751.85 ± 1.59 |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 0 | tg128 | 14.16 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 814.18 ± 1.01 |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.08 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 0 | pp512 | 769.51 ± 0.90 |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 0 | tg128 | 14.15 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-12b-it-UD-Q8_K_XL__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 824.93 ± 0.75 |
| gemma3 12B Q8_0 | 13.40 GiB | 11.77 B | ROCm | 99 | 1 | 0 | tg128 | 14.08 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
hipBLASLt error: Heuristic Fetch Failed!
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 0 | pp512 | 425.33 ± 1.61 |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 0 | tg128 | 4.11 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 470.80 ± 1.97 |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | tg128 | 4.10 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 0 | pp512 | 469.59 ± 0.76 |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 0 | tg128 | 4.04 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 524.38 ± 0.70 |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | tg128 | 4.10 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
hipBLASLt error: Heuristic Fetch Failed!
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 0 | pp512 | 418.14 ± 0.79 |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 0 | tg128 | 4.10 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 472.28 ± 1.24 |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | tg128 | 4.10 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 0 | pp512 | 471.56 ± 0.60 |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 0 | tg128 | 4.10 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 530.58 ± 0.66 |
| gemma3 27B BF16 | 50.31 GiB | 27.01 B | ROCm | 99 | 1 | 0 | tg128 | 4.11 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | pp512 | 2110.44 ± 6.13 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | tg128 | 79.31 ± 0.03 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 2261.02 ± 8.46 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 77.07 ± 0.04 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | pp512 | 2040.30 ± 9.11 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | tg128 | 79.33 ± 0.05 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4-rocwmma__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 2143.83 ± 3.82 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 77.19 ± 0.02 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
rocBLAS error: No hipBLASLt solution found
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | pp512 | 2099.80 ± 6.34 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | tg128 | 79.43 ± 0.05 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 2262.00 ± 6.48 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 77.04 ± 0.03 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | pp512 | 2038.14 ± 6.72 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | tg128 | 79.41 ± 0.04 |
build: 4807e8f9 (6609)
benchmark/results/gemma-3-4b-it-Q3_K_S__rocm6_4_4__hblt0__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 | 2141.85 ± 6.83 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 1 | 0 | tg128 | 77.14 ± 0.02 |
build: 4807e8f9 (6609)
benchmark/results/gpt-oss-120b-F16__rocm6_4_4-rocwmma.log
+15
View File
@@ -0,0 +1,15 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
hipBLASLt error: Heuristic Fetch Failed!
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_HIPBLASLT_ERROR environment variable is set.
rocBLAS warning: hipBlasLT failed, falling back to tensile.
This message will be only be displayed once, unless the ROCBLAS_VERBOSE_TENSILE_ERROR environment variable is set.
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 0 | pp512 | 683.95 ± 7.54 |
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 0 | tg128 | 34.82 ± 0.00 |
build: 4807e8f9 (6609)
benchmark/results/gpt-oss-120b-F16__rocm6_4_4-rocwmma__fa1.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 1 | 0 | pp512 | 783.37 ± 6.29 |
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 1 | 0 | tg128 | 35.06 ± 0.01 |
build: 4807e8f9 (6609)
benchmark/results/gpt-oss-120b-F16__rocm6_4_4-rocwmma__hblt0.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 0 | pp512 | 689.85 ± 4.60 |
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 0 | tg128 | 34.84 ± 0.00 |
build: 4807e8f9 (6609)

Some files were not shown because too many files have changed in this diff Show More