onnxruntime
webgpu: support head_sink in flash attention
#27410
Merged

webgpu: support head_sink in flash attention #27410

guschmue merged 5 commits into main from gs/wgpu-fa-head-sink
guschmue
guschmue support head_sink in flash attention
54a3011a
guschmue guschmue added ep:WebGPU
guschmue guschmue marked this pull request as ready for review 40 days ago
guschmue fix double counting head_sink
900afe7c
guschmue remove unwanted counting of head_sink
64df2fbc
guschmue guschmue requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 35 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-02-24
guschmue Merge branch 'main' into gs/wgpu-fa-head-sink
4f4f984d
fs-eire
fs-eire dismissed these changes on 2026-02-25
guschmue guschmue enabled auto-merge (squash) 35 days ago
guschmue remove unused parameter
e539f4ea
guschmue guschmue dismissed their stale review via e539f4ea 35 days ago
fs-eire
fs-eire approved these changes on 2026-02-25
guschmue guschmue merged bb3866cf into main 35 days ago
guschmue guschmue deleted the gs/wgpu-fa-head-sink branch 35 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone