[CUDA] Update Flash Attention to support head_sink for smooth softmax in GQA#25358
[CUDA] Update Flash Attention to support head_sink for smooth softmax in GQA#25358tianleiwu wants to merge 2 commits into
1 configuration not found
Warning: Code scanning may not have found all the alerts introduced by this pull request, because 1 configuration present on refs/heads/main was not found:
API upload
- ❓ <default>
New alerts in code changed by this pull request
- 1 error
- 1 note
See annotations below for details.
Annotations
Check notice on line 194 in onnxruntime/test/python/transformers/test_gqa.py
Code scanning / CodeQL
Unused local variable Note test
Check failure on line 748 in onnxruntime/test/python/transformers/test_gqa.py
Code scanning / CodeQL
Potentially uninitialized local variable Error test