onnxruntime
webgpu: support head_sink in flash attention
#27410
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
5
Changes
View On
GitHub
webgpu: support head_sink in flash attention
#27410
guschmue
merged 5 commits into
main
from
gs/wgpu-fa-head-sink
support head_sink in flash attention
54a3011a
guschmue
added
ep:WebGPU
guschmue
marked this pull request as ready for review
155 days ago
fix double counting head_sink
900afe7c
remove unwanted counting of head_sink
64df2fbc
guschmue
requested a review
from
copilot-pull-request-reviewer
151 days ago
copilot-pull-request-reviewer
commented on 2026-02-24
Merge branch 'main' into gs/wgpu-fa-head-sink
4f4f984d
fs-eire
dismissed these changes on 2026-02-25
guschmue
enabled auto-merge (squash)
151 days ago
remove unused parameter
e539f4ea
guschmue
dismissed their stale review via
e539f4ea
151 days ago
fs-eire
approved these changes on 2026-02-25
guschmue
merged
bb3866cf
into main
150 days ago
guschmue
deleted the gs/wgpu-fa-head-sink branch
150 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
fs-eire
copilot-pull-request-reviewer
Assignees
No one assigned
Labels
ep:WebGPU
Milestone
No milestone
Login to write a write a comment.
Login via GitHub