Switch to using Cuda Flash Attn for Alibi #1183
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Since 2.4.0.post1, Flash-attn has supported alibi_slopes in its cuda kernels, removing the need for using the triton backend. This PR switches over to using the cuda flash functions rather than triton for compatible flash versions, but retains compatibility for Alibi + flash<2.4.0 via triton for now with a warning.
Future PRs could potentially add the updated Triton implementation from the triton repo which could be faster on H100s, as this is distinct from the triton impl. in the flash attention repo.