projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 0fd1dc4) | patch
Int8 FC performance debugging (#17700)
authorSummer Deng <summerdeng@fb.com>
Sat, 9 Mar 2019 03:00:43 +0000 (19:00 -0800)
committerFacebook Github Bot <facebook-github-bot@users.noreply.github.com>
Sat, 9 Mar 2019 03:03:54 +0000 (19:03 -0800)
commitc10c73f0473baf80305bb800dbee113ff1067a95
treeb6b18cbbf1d0c4123ac3faeb9e64e869e9e0d970tree | snapshot
parent0fd1dc45c037ae806352e08a7b83eeacfad101a0commit | diff
Int8 FC performance debugging (#17700)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/17700

Add performance debugging utilities in DNNLOWP FC operator and the python script

Reviewed By: amylittleyang

Differential Revision: D14321299

fbshipit-source-id: 50dbd7b352a1da5d2ecb659d8003e71e70750063
caffe2/operators/fully_connected_op.h diff | blob | history
caffe2/quantization/server/fully_connected_dnnlowp_op.cc diff | blob | history
Domain: Machine Learning / ML Framework;