0 0 1 Python

Enable Vulkan 4-bit weight only quantization in `export_llama` (#6235)

Summary:
Pull Request resolved: https://github.com/pytorch/executorch/pull/6235

As title.
ghstack-source-id: 248349849
exported-using-ghexport

Reviewed By: jorgep31415

Differential Revision: D64406456

fbshipit-source-id: 20890a7391f821b9b58063bef305909d34d48a18

Stephen Jia committed 1y ago

0a8e007146ff98f2a760b519bbf6ff3b20b43340

Parent: 58ee33d

Committed by Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com> on 10/16/2024, 7:48:15 PM