onnxruntime
Fix unused variable for CUDA EP builds with USE_FLASH_ATTENTION off
#14404
Merged

Fix unused variable for CUDA EP builds with USE_FLASH_ATTENTION off #14404

adrianlizarraga
adrianlizarraga Fix unused variable in bert/attention_impl.cu for builds with USE_FLA…
ffef05f5
adrianlizarraga adrianlizarraga requested a review from tianleiwu tianleiwu 3 years ago
adrianlizarraga adrianlizarraga changed the title Fix unused variable for CUDA EP builds with USE_FLASH_ATTENTION set to OFF Fix unused variable for CUDA EP builds with USE_FLASH_ATTENTION off 3 years ago
adrianlizarraga adrianlizarraga requested a review from yufenglee yufenglee 3 years ago
tianleiwu
tianleiwu approved these changes on 2023-01-23
tianleiwu
adrianlizarraga adrianlizarraga merged 85d7e9c5 into main 3 years ago
adrianlizarraga adrianlizarraga deleted the adrianl/fix-attention-unused-var branch 3 years ago
rui-ren rui-ren added release:1.14
rui-ren rui-ren added triage:approved
faxu faxu removed release:1.14

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone