[Bugfix][CI/Build][Hardware][AMD] Fix AMD tests, add HF cache, update CK FA, add partially supported model notes#6543
Merged
simon-mo merged 12 commits intovllm-project:mainfrom ROCm:mawong/fix_amd_tests_hf_cacheJul 20, 2024
+116-39
Commits
Commits on Jul 20, 2024
- committed
- committed
- committed
- committed
- committed
Update triton to prevent freezes in FA caused by block arg explosion (triton-lang/triton#4176 & triton-lang/triton#4176)
committed- committed
- committed
- committed
- committed
- committed
- committed
