projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: c282aff) | patch
Add support for fusion of half batch norm with float stats (#16735)
authorAdam Paszke <adam.paszke@gmail.com>
Mon, 11 Feb 2019 03:32:15 +0000 (19:32 -0800)
committerFacebook Github Bot <facebook-github-bot@users.noreply.github.com>
Mon, 11 Feb 2019 03:37:57 +0000 (19:37 -0800)
commit8f6ee88a1d14d2f783c65e487b5cbda3f7211980
treecdf6920a1af88f1c56e43ae56d7419cf64f26435tree | snapshot
parentc282afffa79e719e366b869914fc824dbb65684bcommit | diff
Add support for fusion of half batch norm with float stats (#16735)

Summary:
Fixes #16642.

cc ngimel
Pull Request resolved: https://github.com/pytorch/pytorch/pull/16735

Differential Revision: D14020310

Pulled By: ezyang

fbshipit-source-id: ac78726f471d16d188eb998354d52bc79fe2c282
aten/src/ATen/native/cuda/Normalization.cu diff | blob | history
aten/src/ATen/native/cuda/Normalization.cuh diff | blob | history
Domain: Machine Learning / ML Framework;