updated benchmarks
This commit is contained in:
@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
|
||||
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
|
||||
| model | size | params | backend | ngl | fa | test | t/s |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
|
||||
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | pp512 | 4688.15 ± 46.08 |
|
||||
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | tg128 | 134.67 ± 0.48 |
|
||||
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | pp512 | 4529.76 ± 515.81 |
|
||||
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | tg128 | 134.76 ± 0.25 |
|
||||
|
||||
build: fa0465954 (7205)
|
||||
build: 6016d0bd4 (7285)
|
||||
|
||||
Reference in New Issue
Block a user