PR #25777 [webgpu ] Optimize flash attention for Nvidia

[webgpu ] Optimize flash attention for Nvidia #25777

qjia7 merged 9 commits into main from fa_prefill_opt

opt for nv

68a7fb90

limit to nvdia

d4d28403

fix build error

541f0165

indent

443ef7e5

qjia7 marked this pull request as ready for review 1 year ago

qjia7 requested a review from

sushraja-msft 1 year ago

qjia7 requested a review from

guschmue 1 year ago

qjia7 requested a review from

fs-eire 1 year ago

sushraja-msft commented on 2025-08-20

sushraja-msft commented on 2025-08-21

address comments

1e3559f6

address comments

17c3b92e

Merge branch 'main' into fa_prefill_opt

0a6037cd

qjia7 changed the title ~~[webgpu ] Optimize flash attention for NVIDA~~ [webgpu ] Optimize flash attention for Nvidia 1 year ago

add one space before embeded preprocessor

c3fa0b54

qjia7 requested a review from

sushraja-msft 1 year ago

sushraja-msft approved these changes on 2025-08-26

Merge branch 'main' into fa_prefill_opt

2891a504

qjia7 merged cf053667 into main 363 days ago

qjia7 deleted the fa_prefill_opt branch 363 days ago

Reviewers

sushraja-msft

guschmue

fs-eire

Assignees

No one assigned

Labels

None yet

Milestone

No milestone