updated benchs
This commit is contained in:
@@ -4,7 +4,7 @@ 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 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 1234.38 ± 12.52 |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 27.25 ± 0.00 |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 1274.89 ± 11.66 |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 27.18 ± 0.00 |
|
||||
|
||||
build: 4807e8f9 (6609)
|
||||
build: 11f0af55 (6736)
|
||||
|
||||
Reference in New Issue
Block a user