pytorch
727e77a8 - [quant] Enable reduce_range for graphmode (#39874)

Commit

4 years ago

[quant] Enable reduce_range for graphmode (#39874) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/39874 When fbgemm backend is set we make sure reduce_range is set to true to avoid overflow in the operator Also adds test for per-channel quant with graph mode and compare numerics with eager mode Test Plan: python test/test_quantization.py Imported from OSS Differential Revision: D22011205 fbshipit-source-id: 1c7c9b7ab0d84200e3d8d85c34978554c30c0169

Author

supriyar

Committer

facebook-github-bot

Parents

b2620722

Files5

aten/src/ATen/native/quantized
- QTensor.cpp
test/quantization
- test_quantize.py
- test_quantize_script.py
torch
- csrc/jit/passes/quantization
  - insert_quant_dequant.cpp
- quantization
  - qconfig.py

pytorch 727e77a8 - [quant] Enable reduce_range for graphmode (#39874)

pytorch
727e77a8 - [quant] Enable reduce_range for graphmode (#39874)