Add fold_quantize=True for all convert_pt2e calls (#1640)
Summary: X-link: https://github.com/pytorch/pytorch/pull/117797 Pull Request resolved: https://github.com/pytorch/executorch/pull/1640 In preparation for enabling fold_quantize=True by default Reviewed By: andrewor14 Differential Revision: D52879612 fbshipit-source-id: a3db1319b8ee4fac713946453eafdcd437f63a7e
J
Jerry Zhang committed
017bf8d8d9412730879dfe43a221a9cb2b6ae86e
Parent: 72c017f
Committed by Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
on 1/24/2024, 5:45:57 PM