pytorch

e816e176 - [PyTorch] Add native fast path for transformer encoder inference (#76333)

[PyTorch] Add native fast path for transformer encoder inference (#76333) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/76333 The current PyTorch multi-head attention and transformer implementations are slow. This should speed them up for inference. ghstack-source-id: 154737857 (Note: this ignores all push blocking failures!) Test Plan: CI Reviewed By: cpuhrsch Differential Revision: D35239925 fbshipit-source-id: 5a7eb8ff79bc6afb4b7d45075ddb2a24a6e2df28