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

- Corrected typo in WMMA (was spelt wrong as waam)

Browse Source 
- Included rocm-7rc-rocwmma toolbox
- Included updated results from benchmarks including rocm 7rc with ROMWMMA and hipBLASLt
This commit is contained in:
Donato Capitella
2025-08-10 13:21:06 +01:00
parent 19fc866a9d
commit a9618d881b
619 changed files with 16448 additions and 4651 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/gpt-oss-20b-F32__rocm6_4_2-rocwmma__fa1.log
+3 -3
View File
@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 999 | 1 | 0 | pp512 | 380.87 ± 8.21 |
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 999 | 1 | 0 | tg128 | 26.79 ± 0.00 |
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 343.30 ± 5.27 |
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 26.76 ± 0.00 |
build: cd6983d5 (6119)
build: 79c1160b (6123)