Add split reduction kernel for Flash Attention decoding #671
Conversation
This file contains hidden or 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
each work group handles whole group query heads and packing group query heads into single MMA call
wuxun-zhang
force-pushed
the
wuxun/split-reduction-kernel
branch
from
11ab8d0 to
2ad4764
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Description
This PR aims to add new split reduction kernel for flash attention which benefits for long context length scenario.
Note: Codes are not cleaned but ready for testing.
What's newly added in this PR
XeFMHAFwdSplitKVKernelReduceSplitKXeReduceSplitKTileSchedulerLimitation
Type
Testing
Performance
References
Fixes #
Checklist