[Pytorch Edge] Quantized Ops Dtype Selective (#63680)
authorJacob Szwejbka <jakeszwe@fb.com>
Mon, 13 Sep 2021 17:54:08 +0000 (10:54 -0700)
committerFacebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
Mon, 13 Sep 2021 18:04:07 +0000 (11:04 -0700)
commitfd716fcda2f030e6f0913fc6c687005d108282c5
treed8bf5508e03d8e19e54231a9e87882a58de9d893
parent4ca40aeb83db53424b6f5ec3820019f79c15df46
[Pytorch Edge] Quantized Ops Dtype Selective (#63680)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/63680

Quantized ops not covered by DType Selectivity. Add the check, and adjust call sites to be constexpr friendly.

Test Plan: CI (this covers all model unit tests), verified that segmentation (a model that uses some of these quant ops) still works on instagram.

Reviewed By: dhruvbird, raymondethan

Differential Revision: D30457626

fbshipit-source-id: 5ba850d2b53a18558dfbb1cfaa78d8f53b5dbad8
aten/src/ATen/Dispatch.h
aten/src/ATen/native/quantized/affine_quantizer.cpp
aten/src/ATen/native/quantized/cpu/kernels/QuantizedOpKernels.cpp
aten/src/ATen/native/quantized/cuda/affine_quantizer.cu