pytorch

1ec4337b - Use Int8QuantParamsBlob to pass the scale and zeropoint params (#40390)

Use Int8QuantParamsBlob to pass the scale and zeropoint params (#40390) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/40390 Change the Int8FC/Int8Quantize op interface to use Int8QuantParamsBlob as the qparam input blob format when needed. Test Plan: ``` buck test caffe2/caffe2/quantization/server: ``` Reviewed By: hx89 Differential Revision: D22124313 fbshipit-source-id: 6b5c1974c0fc5928f72773495f0da8d0eb9b98c9