onnxruntime
[webgpu] Use workgroup memory to reduce register pressure
#24286
Merged

[webgpu] Use workgroup memory to reduce register pressure #24286

sushraja-msft merged 9 commits into main from opt_flash_attention
qjia7
qjia7 [webgpu] Use workgroup memory to reduce register pressure
3e0c090b
sushraja-msft
sushraja-msft commented on 2025-04-03
sushraja-msft
sushraja-msft commented on 2025-04-03
qjia7 address comments
a0c608cb
qjia7 qjia7 marked this pull request as ready for review 1 year ago
guschmue guschmue added ep:WebGPU
sushraja-msft
sushraja-msft
sushraja-msft requested changes on 2025-04-04
qjia7 Merge branch 'main' into opt_flash_attention
5b2676b6
qjia7 address comments
52391bf3
qjia7 qjia7 requested a review from sushraja-msft sushraja-msft 1 year ago
qjia7 qjia7 requested a review from guschmue guschmue 1 year ago
sushraja-msft
sushraja-msft commented on 2025-04-09
sushraja-msft
sushraja-msft dismissed these changes on 2025-04-09
qjia7 address comments
a3b610ff
qjia7 qjia7 dismissed their stale review via a3b610ff 1 year ago
qjia7
qjia7 Merge branch 'main' into opt_flash_attention
3eb71395
qjia7 limit the changes to qualcomm
cd16e958
qjia7 qjia7 requested a review from sushraja-msft sushraja-msft 1 year ago
sushraja-msft
sushraja-msft dismissed these changes on 2025-04-10
guschmue
guschmue dismissed these changes on 2025-04-10
guschmue
azure-pipelines
guschmue
guschmue
azure-pipelines
guschmue
azure-pipelines
guschmue
azure-pipelines
guschmue
qjia7 Merge branch 'main' into opt_flash_attention
8d99db7d
guschmue
qjia7 fix build errors
a2dd5982
qjia7 qjia7 dismissed their stale review via a2dd5982 1 year ago
qjia7 qjia7 dismissed their stale review via a2dd5982 1 year ago
guschmue
guschmue approved these changes on 2025-04-11
sushraja-msft sushraja-msft merged 2d5316f1 into main 1 year ago
sushraja-msft sushraja-msft deleted the opt_flash_attention branch 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone