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

updated benchmarks

Browse Source
This commit is contained in:
Donato Capitella
2025-11-30 13:47:32 +00:00
parent 301424c1f7
commit 3d9087c39b
184 changed files with 3159 additions and 3222 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/gpt-oss-20b-F32__rocm-7.9__hblt0__fa1__dual.log
+2 -2
View File
@@ -5,7 +5,7 @@ ggml_cuda_init: found 2 ROCm devices:
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | pp512 | 568.37 ± 3.91 |
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | tg128 | 61.73 ± 0.09 |
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | pp512 | 560.29 ± 11.45 |
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | tg128 | 61.74 ± 0.09 |
build: fa0465954 (7205)