[webgpu] Enable indirect dispatch for flash attention #26207
Merged
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
guschmue
approved these changes
Oct 13, 2025
qjia7
commented
Oct 14, 2025
There was a problem hiding this comment.
Thanks for your comments @sushraja-msft. My reply inserted. I am going to merge this PR to unblock my following work as we discussed offline. @sushraja-msft @fs-eire Please continue your review if you have more comments. I will follow up them separately.
fs-eire
pushed a commit
that referenced
this pull request
Oct 24, 2025
This pull request introduces support for indirect dispatch in the WebGPU FlashAttention implementation, enabling more dynamic and efficient kernel launches based on runtime sequence lengths. The changes add new logic and parameters to propagate sequence length information and indirect dispatch buffers through the attention pipeline, with conditional code paths to maintain compatibility with the existing direct dispatch approach. It's part of the work to enable graph capture in phi4 #25868
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Outdated suggestions cannot be applied.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.
This pull request introduces support for indirect dispatch in the WebGPU FlashAttention implementation, enabling more dynamic and efficient kernel launches based on runtime sequence lengths. The changes add new logic and parameters to propagate sequence length information and indirect dispatch buffers through the attention pipeline, with conditional code paths to maintain compatibility with the existing direct dispatch approach.
It's part of the work to enable graph capture in phi4 #25868