Jerry Zhang dfcd7b0185 QTensor (#18230) ...

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/18230

Implementing minimum qtensor API to unblock other workstreams in quantization

Changes:
- Added Quantizer which represents different quantization schemes
- Added qint8 as a data type for QTensor
- Added a new ScalarType QInt8
- Added QTensorImpl for QTensor
- Added following user facing APIs
  - quantize_linear(scale, zero_point)
  - dequantize()
  - q_scale()
  - q_zero_point()

Reviewed By: dzhulgakov

Differential Revision: D14524641

fbshipit-source-id: c1c0ae0978fb500d47cdb23fb15b747773429e6c

2019-04-03 13:17:11 -07:00

..

caffe2

Optimize images (#14084)

2018-12-05 22:46:32 -08:00

cpp

Turn on F401: Unused import warning. (#18598)

2019-03-30 09:01:17 -07:00

source

QTensor (#18230)

2019-04-03 13:17:11 -07:00

libtorch.rst

Fix possible importing errors in build_libtorch.py (#15471)

2019-01-16 23:55:57 -08:00

make.bat

Add Sphinx docs

2016-12-28 00:03:39 +01:00

Makefile

Rewrite http://pytorch.org -> https://pytorch.org throughout project (#12636)

2018-10-15 13:03:27 -07:00

requirements.txt

Unpin Sphinx. (#13831)

2018-11-13 09:45:12 -08:00