Skip to content

[webgpu] Use 1D dispatch groups for attention #24228

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 7, 2025

Conversation

qjia7
Copy link
Contributor

@qjia7 qjia7 commented Mar 28, 2025

This PR uses 1d disptach group size and uses workgroup_idx instead of workgroup.x|workgroup.y in case they are normalized.

@guschmue guschmue added the ep:WebGPU ort-web webgpu provider label Mar 28, 2025
@snnn snnn closed this Apr 3, 2025
@snnn snnn reopened this Apr 3, 2025
fs-eire
fs-eire previously approved these changes Apr 4, 2025
@fs-eire fs-eire merged commit a1186f6 into main Apr 7, 2025
87 of 89 checks passed
@fs-eire fs-eire deleted the attention_1d_dispatch_groups branch April 7, 2025 13:36
quic-zhaoxul pushed a commit to CodeLinaro/onnxruntime that referenced this pull request Apr 17, 2025
This PR uses 1d disptach group size and uses workgroup_idx instead of
workgroup.x|workgroup.y in case they are normalized.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ep:WebGPU ort-web webgpu provider
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants