Skip to content

[executorch][cuda] fuse gate/up MLP projections #20482

Open
Gasoonjia wants to merge 1 commit into
gemma4_31b_export_under_32gbfrom
gemma4_31b-cuda-decode-speedup
Open

[executorch][cuda] fuse gate/up MLP projections #20482
Gasoonjia wants to merge 1 commit into
gemma4_31b_export_under_32gbfrom
gemma4_31b-cuda-decode-speedup

[executorch][cuda] gemma4_31b: fuse gate/up MLP projections (default-on)

1c371e2
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar