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__rocm7.1.1-rocwmma__fa1__longctx32768__single.log
+3 -3
View File
@@ -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 | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 1083.90 ± 0.00 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 92.69 ± 0.00 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 1063.94 ± 0.00 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 96.13 ± 0.00 |
build: 22577583a (7312)
build: 2aa45ef9e (7423)