transformers
Flash-attn performance: remove cuda sync during inference
#33570
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
1
Changes
View On
GitHub
Flash-attn performance: remove cuda sync during inference
#33570
Cyrilvallez
merged 1 commit into
huggingface:main
from
Cyrilvallez:fix-flash
Switch conditions to use short-circuit during inference
a55d5f24
ArthurZucker
approved these changes on 2024-09-20
Cyrilvallez
merged
1f33023c
into main
2 years ago
Login to write a write a comment.
Login via GitHub
Reviewers
ArthurZucker
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub