[CUDA] Update Flash Attention to support head_sink for smooth softmax in GQA#25358
Closed
tianleiwu wants to merge 2 commits into
Closed
[CUDA] Update Flash Attention to support head_sink for smooth softmax in GQA#25358tianleiwu wants to merge 2 commits into
tianleiwu wants to merge 2 commits into
GitHub Advanced Security / lintrunner
succeeded
Jul 10, 2025 in 4s
1 new alert
New alerts in code changed by this pull request
- 1 note
See annotations below for details.
Annotations
Check notice on line 180 in onnxruntime/test/python/transformers/test_gqa.py
Code scanning / lintrunner
RUFF/PLC0415 Note test
Loading