Files
pytorch/caffe2/python/layers
Xing Wang 73ae23a4ea add support for real4bits quant (#25426)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/25426

Add embedding table 4bit quantization support.

* add the conversion from fp32 to int4.
* using brew to pass the context so that the 4bit operators are added when generating the predictor net.

Reviewed By: kennyhorror, chocjy

Differential Revision: D16859892

fbshipit-source-id: a06c3f0b56a7eabf9ca4a2b2cb6c63735030d70b
2019-09-20 13:45:23 -07:00
..
2019-08-25 01:42:25 -07:00
2019-08-15 23:20:15 -07:00