[nnpi eval] enable int8 eval with emulation Int8FC (#39112)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39112
Allow int8 packed weights in int8 model to deserialize to original format. Set default deserialization behavior in eval workflows to original format.
Test Plan: Tested with workflow: f192797187
Reviewed By: yinghai
Differential Revision: D21737940
fbshipit-source-id: 7afaf307b16cb4e85e61f019356f83fdab772c57