cjw/amd-r9700-ai-toolboxes
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity

benchmakr updates

Browse Source
This commit is contained in:
Donato Capitella
2025-12-17 08:01:12 +00:00
parent 29da348bb8
commit 2e8bef127f
818 changed files with 30850 additions and 24154 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/gpt-oss-20b-mxfp4__rocm-7.9__fa1__single.log
+3 -3
View File
@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, 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 | 4335.90 ± 567.42 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | tg128 | 132.77 ± 0.28 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | pp512 | 4475.05 ± 86.25 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | tg128 | 134.51 ± 0.54 |
build: 6016d0bd4 (7285)
build: 2aa45ef9e (7423)