updated benchs

This commit is contained in:
Donato Capitella
2025-10-12 07:39:42 +01:00
parent e1f5aaa85c
commit 765cc5c733
545 changed files with 10701 additions and 22399 deletions
@@ -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 | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 1215.59 ± 8.93 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 67.39 ± 0.00 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 1239.97 ± 8.69 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 67.10 ± 0.01 |
build: f1fbffb5 (6486)
build: a3cb0474 (6735)