[webgpu] Simplify the signature of CanApplyFlashAttention - #26926
Merged
Conversation
guschmue
approved these changes
Jan 7, 2026
qjia7
marked this pull request as ready for review
January 8, 2026 01:43
alex-spacemit
pushed a commit
to spacemit-com/onnxruntime
that referenced
this pull request
Jan 20, 2026
…26926) This pull request simplifies the logic for handling present key/value tensors in the WebGPU Flash Attention implementation. The main change is that the responsibility for creating internal present key/value tensors is moved from the caller to the `ApplyFlashAttention` function itself. This reduces code duplication and makes the API easier to use. Additionally, the `CanApplyFlashAttention` function is simplified to remove unnecessary checks for present key/value tensors.
alex-spacemit
pushed a commit
to spacemit-com/onnxruntime
that referenced
this pull request
Jan 27, 2026
…26926) This pull request simplifies the logic for handling present key/value tensors in the WebGPU Flash Attention implementation. The main change is that the responsibility for creating internal present key/value tensors is moved from the caller to the `ApplyFlashAttention` function itself. This reduces code duplication and makes the API easier to use. Additionally, the `CanApplyFlashAttention` function is simplified to remove unnecessary checks for present key/value tensors.
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 simplifies the logic for handling present key/value tensors in the WebGPU Flash Attention implementation. The main change is that the responsibility for creating internal present key/value tensors is moved from the caller to the
ApplyFlashAttentionfunction itself. This reduces code duplication and makes the API easier to use. Additionally, theCanApplyFlashAttentionfunction is simplified to remove unnecessary checks for present key/value tensors.