julian/amd-strix-halo-toolboxes
1
0
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

updated benchmarks

Browse Source
This commit is contained in:
Donato Capitella
2026-02-09 13:30:26 +00:00
parent 632130a2c3
commit 8ff812fbb5
204 changed files with 1645 additions and 1376 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/gpt-oss-20b-mxfp4__rocm-7_2__fa1__longctx32768.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), 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 | 402.32 ± 0.67 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 52.50 ± 0.02 |
build: e0c93af2a (7938)