Use Linear Operator with fp16 weights in JIT (#22323)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/22323
This diff adds an interface to use quantized Linear op in JIT.
Reviewed By: jamesr66a
Differential Revision: D16040724
fbshipit-source-id: 90e90aff9973c96ea076ed6a21ae02c349ee2bcf