[executorch][cuda] Route 2-D depthwise and few-channel grouped convolutions to a Triton direct-stencil kernel - #25085

[executorch][cuda] Route 2-D depthwise and few-channel grouped convolutions to a Triton direct-stencil kernel#25085

Gasoonjia wants to merge 2 commits into

gh/Gasoonjia/111/basepytorch/executorch:gh/Gasoonjia/111/basefrom

gh/Gasoonjia/111/headpytorch/executorch:gh/Gasoonjia/111/headCopy head branch name to clipboard