Jerry Zhang
0804452709
fix lint in torch/nn/quantized/modules/linear.py ( #22325 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/22325
att
Reviewed By: bddppq
Differential Revision: D16042464
fbshipit-source-id: 0610896c08667fdaa95983f49140193ecb9ede16
2019-06-27 23:18:42 -07:00
Jerry Zhang
5e77111486
nn.quantized.Relu and nn.quantize.Quantize/DeQuantize modules
...
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/21930
Differential Revision: D15554224
fbshipit-source-id: 1de9ac7412468106be60e53852c23318ead37bc6
2019-06-27 16:15:17 -07:00
Jerry Zhang
2832e33a94
Add serialization for nn.quantized.Linear module ( #21925 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/21925
att
Differential Revision: D15483071
fbshipit-source-id: 3a218dad5b653b38a0885339889ff70c75a13bef
2019-06-27 14:57:22 -07:00
Jerry Zhang
5c46e701fc
Implementation of nn.quantized.linear module ( #21921 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/21921
Call FBGEMM kernels to implement quantized linear operator. This operator is used only for inference.
Differential Revision: D15375695
fbshipit-source-id: b9ca6c156fd60481fea83e55603b2897f7bfc3eb
2019-06-27 14:09:48 -07:00
