Support 2CTA for sliding window hdim 192#2347
Merged
tridao merged 4 commits intoDao-AILab:mainfrom Mar 19, 2026
Merged
Conversation
Member
Collaborator
@tridao Sorry, there wasn't a good reason, I was thinking there might be issues with tile scheduling but that's not the case. It seems good to just disable the asserts and use the code as is for local. In fact, we could also use 2CTA for hdim 128 local. |
Member
|
Can you enable the tests that will hit this code path? |
tridao
approved these changes
Mar 18, 2026
Member
|
LGTM, we can merge when it's ready |
zhuochenKIDD
pushed a commit
to zhuochenKIDD/flash-attention
that referenced
this pull request
Mar 25, 2026
* Support 2CTA for sliding window hdim 192 * Remove local 2CTA restriction in SM100 backward * Enable SM100 backward local tests for hdim 192
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #2286
Keep 2CTA enabled for SM100 backward sliding window when
head_dim = 192, which avoids theMust use 2CTA for hdim 192assertion.Validated on B300 with the given repro.