[quant] Add op support for linear_relu_dynamic_fp16 (#63824)
authorSupriya Rao <supriyar@fb.com>
Fri, 27 Aug 2021 04:05:56 +0000 (21:05 -0700)
committerFacebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
Fri, 27 Aug 2021 04:12:04 +0000 (21:12 -0700)
commitcec44aa574e06e8aa1096b62a7c6d7c4dda8a3f5
tree22cfe6bf6f0bdec6028cb144ae81307d88f855d5
parent975f4ccad6fb7ca13c50ee628ec3fb3a77a64893
[quant] Add op support for linear_relu_dynamic_fp16 (#63824)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/63824

Add a fused operator implementation that will work with the quantization fusion APIs.
Once FBGEMM FP16 kernel supports relu fusion natively we can remove the addition from the PT operator.

Test Plan:
python test/test_quantization.py

Imported from OSS

Reviewed By: heitorschueroff

Differential Revision: D30503514

fbshipit-source-id: 6bf3bd53f47ffaa3f1d178eaad8cc980a7f5258a
aten/src/ATen/native/quantized/cpu/qlinear_dynamic.cpp
aten/src/ATen/native/quantized/library.cpp
test/quantization/core/test_quantized_op.py