qlinear: Remove legacy cpp_custom_type_hack support (#72680)
Summary:
Ref https://github.com/pytorch/pytorch/issues/72263 for cpp_custom_type_hack removal
`qlinear_prepack` and `qlinear_unpack` were updated to use torchbind
and the `cpp_custom_type_hack` overloads marked with a deprecation
warning in https://github.com/pytorch/pytorch/issues/38101 which was in the PyTorch 1.6 release. So, we are
safe to break BC here.
The deprecation warning only appears in unpack, but you can't use one
without the other I think that's still okay.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/72680
Reviewed By: george-qi
Differential Revision: D35056994
Pulled By: jerryzh168
fbshipit-source-id: cc046b9fa00d0219a4510854204564f4ea23da4b
(cherry picked from commit 31abbf1142d86174a1980feced57e4c621b704d1)