0 0 1 Python

Better 4bit packing (#2649)

Summary:
Pull Request resolved: https://github.com/pytorch/executorch/pull/2649

Just use tensor methods, drop custom op and the previous python logic

Also drop aot_utils for xnnpack

Reviewed By: kimishpatel, GregoryComer

Differential Revision: D55319010

fbshipit-source-id: 4b56b0fd19e628f2577dea0529fbf93518701d2f

Digant Desai committed 2y ago

3c64e8f0cf13545c199f6484abd9e9ad8f07f5cc

Parent: 7149a9c

Committed by Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com> on 3/27/2024, 3:32:52 PM