onnxruntime
[webgpu] Fix poor performance in flash attention for Qualcomm devices
#25730
Merged

[webgpu] Fix poor performance in flash attention for Qualcomm devices #25730

qjia7 merged 2 commits into main from fa_prefill_opt
qjia7
qjia7 Fix poor performance in flash attention for Qualcomm devices
b4a7c0b3
qjia7 qjia7 requested a review from sushraja-msft sushraja-msft 303 days ago
qjia7 qjia7 requested a review from guschmue guschmue 303 days ago
qjia7 only for qualcomm
19a871bc
guschmue guschmue added ep:WebGPU
sushraja-msft
sushraja-msft approved these changes on 2025-08-15
qjia7 qjia7 merged a61fb39e into main 301 days ago
qjia7 qjia7 deleted the fa_prefill_opt branch 301 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone