0 0 1 Python

Add kvcache to llama2 (#1619)

Summary:
Pull Request resolved: https://github.com/pytorch/executorch/pull/1619

Add kvcache as IO to llama2.

Reviewed By: kimishpatel

Differential Revision: D52577122

fbshipit-source-id: 9b7d222c26b76a6302f91a21189abcb6b446c88c

Jacob Szwejbka committed 2y ago

927e2a12871669487a7e59c3e9dcf6461fd16023

Parent: d447737

Committed by Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com> on 1/18/2024, 8:41:41 PM