[Inductor] add config for weight prepacking (#93811)
Fixes #93495
Mkldnn weight prepacking may lead to large memory footprint for some models such as UniXcoder. In this case, disabling mkldnn weight prepacking is needed to avoid memory overload.
This PR adds a config for switching mkldnn weight prepacking.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/93811
Approved by: https://github.com/jgong5, https://github.com/jansel