[webgpu] Apply Flash Attention if sliding window exceeds KV cache length #25594
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
qjia7
reviewed
Jul 30, 2025
qjia7
reviewed
Jul 31, 2025
guschmue
approved these changes
Jul 31, 2025
|
/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline |
|
Azure Pipelines successfully started running 5 pipeline(s). |
|
CI infra issue by check the logs, please help to re-run. |
snnn
pushed a commit
that referenced
this pull request
Aug 1, 2025
…gth (#25594) ### Description <!-- Describe your changes. --> #25372 adds sliding window support for Group Query Attention, disabling Flash Attention as it's not yet supported. This PR adds a check for the sliding window and applies Flash Attention when the window size exceeds the KV cache length or total sequence length. ### Motivation and Context See above.
snnn
added a commit
that referenced
this pull request
Aug 1, 2025
This PR cherry-picks some pipeline changes from the main branch to the 1.23.0 release branch. - **[build] disable CodeQL for NPM Packaging Pipeline (#25614)** - **Refactor Java Test Pipeline (#25608)** - **[build] upgrade Node.js for NPM packaging pipeline (#25568)** And a WebGPU change: - **[webgpu] Apply Flash Attention if sliding window exceeds KV cache length (#25594)**
sanketkaleoss
pushed a commit
to sanketkaleoss/onnxruntime
that referenced
this pull request
Aug 11, 2025
…gth (microsoft#25594) ### Description <!-- Describe your changes. --> microsoft#25372 adds sliding window support for Group Query Attention, disabling Flash Attention as it's not yet supported. This PR adds a check for the sliding window and applies Flash Attention when the window size exceeds the KV cache length or total sequence length. ### Motivation and Context See above.
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.
Description
#25372 adds sliding window support for Group Query Attention, disabling Flash Attention as it's not yet supported.
This PR adds a check for the sliding window and applies Flash Attention when the window size exceeds the KV cache length or total sequence length.
Motivation and Context
See above.