Updated benchmarks
This commit is contained in:
@@ -4,7 +4,7 @@ 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 ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 999 | 1 | 0 | pp512 | 1502.62 ± 12.84 |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 999 | 1 | 0 | tg128 | 26.67 ± 0.00 |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 1481.17 ± 9.67 |
|
||||
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 27.03 ± 0.00 |
|
||||
|
||||
build: 34c9d765 (6122)
|
||||
build: de219279 (6181)
|
||||
|
||||
Reference in New Issue
Block a user