Updated benchmarks
This commit is contained in:
@@ -2,9 +2,9 @@ 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: AMD Radeon 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 | 770.55 ± 4.47 |
|
||||
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 1 | 0 | tg128 | 35.07 ± 0.00 |
|
||||
| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | pp512 | 775.86 ± 2.82 |
|
||||
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | tg128 | 37.40 ± 0.01 |
|
||||
|
||||
build: a3cb0474 (6735)
|
||||
build: bca95ca51 (7036)
|
||||
|
||||
Reference in New Issue
Block a user