onnxruntime
webgpu: Support QKV bias in FlashAttention for MultiHeadAttention
#28380
Merged

webgpu: Support QKV bias in FlashAttention for MultiHeadAttention #28380

guschmue merged 2 commits into main from webgpu-flash-attention-bias
qjia7
qjia7 webgpu: Support QKV bias in FlashAttention for MultiHeadAttention
4446c8b5
qjia7 webgpu: Remove unused bias parameter from CanApplyFlashAttention
a07c8a31
qjia7 qjia7 requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 48 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-05-06
qjia7 qjia7 requested a review from guschmue guschmue 48 days ago
qjia7 qjia7 requested a review from hariharans29 hariharans29 48 days ago
guschmue guschmue added ep:WebGPU
guschmue
guschmue approved these changes on 2026-05-06
guschmue guschmue merged 3b007a68 into main 48 days ago
guschmue guschmue deleted the webgpu-flash-attention-bias branch 48 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone