updated benchmarks
This commit is contained in:
@@ -5,7 +5,7 @@ ggml_cuda_init: found 2 ROCm devices:
|
||||
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | fa | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | pp512 | 3463.77 ± 25.73 |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | tg128 | 61.77 ± 0.07 |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | pp512 | 3449.20 ± 31.03 |
|
||||
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | tg128 | 61.78 ± 0.06 |
|
||||
|
||||
build: fa0465954 (7205)
|
||||
|
||||
Reference in New Issue
Block a user