tree 9517b3d651b91c19c3335856b25a29783501e428
parent 68397af396aca6cb7c8326da5ba29da0ffcf2d23
author Scott Wolchok <swolchok@meta.com> 1726031763 -0700
committer Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com> 1726031763 -0700

Add optimized op_linear (#5243)

Summary:
Pull Request resolved: https://github.com/pytorch/executorch/pull/5243

If we happen to be running without a delegate, directly implementing linear is much more efficient than permute_copy_out (materialize a transpose) followed by matmul.
ghstack-source-id: 241918986
exported-using-ghexport

Reviewed By: kimishpatel

Differential Revision: D62154007

fbshipit-source-id: 7b764cf9de616729541f081a51384ba8e18e72f5