Replies: 2 comments
-
According to the tweet it does, and by a pretty good margin too! |
Beta Was this translation helpful? Give feedback.
0 replies
-
It appears to be in xformers now? @vladmandic any thoughts? I realize tensorrt is going to be faster but also a pain in the rear. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
https://twitter.com/_akhaliq/status/1680988185776607237
https://tridao.me/publications/flash2/flash2.pdf
https://github.com/Dao-AILab/flash-attention
Beta Was this translation helpful? Give feedback.
All reactions