projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 159c2f3) | patch
Minor bug fix in dnnlowp (#15841)
authorSummer Deng <summerdeng@fb.com>
Thu, 10 Jan 2019 01:11:53 +0000 (17:11 -0800)
committerFacebook Github Bot <facebook-github-bot@users.noreply.github.com>
Thu, 10 Jan 2019 01:18:30 +0000 (17:18 -0800)
commit5af9aaa5bbfbad51f420acde0f992279404032e5
tree67e262d0b3ce8825fd7d45d676f429b51f778d55tree | snapshot
parent159c2f39189bfb95a50548c008f40ac523fc752dcommit | diff
Minor bug fix in dnnlowp (#15841)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/15841

Fix the bugs in dnnlowp to support int8/int16 quantization for sparsenn.

Reviewed By: jspark1105

Differential Revision: D13600878

fbshipit-source-id: 27f06d7c54a663208320c8f211714220a9b49540
caffe2/quantization/server/dnnlowp.cc diff | blob | history
caffe2/quantization/server/dnnlowp_op.h diff | blob | history
Domain: Machine Learning / ML Framework;