transformers
Flash-attn performance: remove cuda sync during inference
#33570
Merged

Flash-attn performance: remove cuda sync during inference #33570

Cyrilvallez
Cyrilvallez Switch conditions to use short-circuit during inference
a55d5f24
HuggingFaceDocBuilderDev
Cyrilvallez
ArthurZucker
ArthurZucker approved these changes on 2024-09-20
Cyrilvallez Cyrilvallez merged 1f33023c into main 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone