Skip to content

[cuda backend] skip fully-masked KV blocks calculation in SDPA#20198

Open
Gasoonjia wants to merge 7 commits into
mainfrom
g4-opt-prefill-window-sdpa
Open

[cuda backend] skip fully-masked KV blocks calculation in SDPA#20198
Gasoonjia wants to merge 7 commits into
mainfrom
g4-opt-prefill-window-sdpa

Merge branch 'main' into g4-opt-prefill-window-sdpa

8029941
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar