neclean up of legacy toolboxes, removal of rocwmma and renamed rocm7-alpha to rocm-7nightlies. Added new benchmarks
This commit is contained in:
+10
@@ -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 | 330.74 ± 2.03 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.74 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 330.13 ± 0.85 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.73 ± 0.01 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 333.45 ± 1.70 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.33 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 336.20 ± 2.04 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.77 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 323.36 ± 0.16 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.68 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 323.91 ± 1.10 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.68 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 330.90 ± 1.42 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.83 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 329.23 ± 1.32 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 21.83 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+8
@@ -0,0 +1,8 @@
|
||||
ggml_vulkan: Found 1 Vulkan devices:
|
||||
ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
|
||||
| model | size | params | backend | ngl | fa | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | Vulkan | 99 | 1 | 0 | pp512 | 228.89 ± 0.52 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | Vulkan | 99 | 1 | 0 | tg128 | 24.48 ± 0.01 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+8
@@ -0,0 +1,8 @@
|
||||
ggml_vulkan: Found 1 Vulkan devices:
|
||||
ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
|
||||
| model | size | params | backend | ngl | fa | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | Vulkan | 99 | 1 | 0 | pp512 | 243.57 ± 0.43 |
|
||||
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | Vulkan | 99 | 1 | 0 | tg128 | 24.54 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 275.04 ± 0.75 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.57 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 272.75 ± 1.25 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.56 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 277.38 ± 0.34 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.52 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 277.33 ± 0.75 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.62 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 254.32 ± 0.84 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.51 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 253.04 ± 1.12 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.50 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 257.70 ± 0.50 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.59 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 259.40 ± 0.46 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | ROCm | 99 | 1 | 0 | tg128 | 16.61 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+8
@@ -0,0 +1,8 @@
|
||||
ggml_vulkan: Found 1 Vulkan devices:
|
||||
ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
|
||||
| model | size | params | backend | ngl | fa | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | Vulkan | 99 | 1 | 0 | pp512 | 279.25 ± 0.28 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | Vulkan | 99 | 1 | 0 | tg128 | 17.61 ± 0.01 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+8
@@ -0,0 +1,8 @@
|
||||
ggml_vulkan: Found 1 Vulkan devices:
|
||||
ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
|
||||
| model | size | params | backend | ngl | fa | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | Vulkan | 99 | 1 | 0 | pp512 | 244.36 ± 0.45 |
|
||||
| glm4moe 106B.A12B Q6_K | 94.57 GiB | 110.47 B | Vulkan | 99 | 1 | 0 | tg128 | 17.73 ± 0.01 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 145.84 ± 0.07 |
|
||||
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.78 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 144.36 ± 0.18 |
|
||||
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.78 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 145.01 ± 0.05 |
|
||||
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.77 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 146.28 ± 0.12 |
|
||||
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.78 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 146.01 ± 0.05 |
|
||||
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 143.94 ± 0.16 |
|
||||
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 147.07 ± 0.01 |
|
||||
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
+10
@@ -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 | 145.12 ± 0.04 |
|
||||
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 1 | 0 | tg128 | 2.79 ± 0.00 |
|
||||
|
||||
build: 2aa45ef9e (7423)
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user