update benchmarks

This commit is contained in:
Donato Capitella
2026-04-11 11:18:45 +01:00
parent a821bcb91d
commit 7aa6e6dea9
514 changed files with 7863 additions and 13522 deletions
@@ -2,7 +2,7 @@ ggml_cuda_init: found 1 ROCm devices (Total VRAM: 126976 MiB):
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, VRAM: 126976 MiB
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 1691.01 ± 16.68 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 72.07 ± 0.01 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 1694.78 ± 17.20 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 72.19 ± 0.02 |
build: 2405d59cb (8577)
build: 3f8752b55 (8743)