pytorch

60cadd0b - [fx2trt] Refactor linear op to use mm + add

[fx2trt] Refactor linear op to use mm + add Summary: Previously linear is translated to fully_connected which only works when weight is a constant, this diff changes that to mm + add so that the weight can be an ITensor so that we can have the weight - quantize - dequantize pattern in the produced TensorRT network Test Plan: buck run mode/opt caffe2/torch/fb/fx2trt:test_linear Reviewed By: 842974287 Differential Revision: D30294751 fbshipit-source-id: 596fbd4c81caef8df41a002a2e14fbf22d9d2a80