review.tizen.org Git - platform/upstream/pytorch.git/commit

projects / platform / upstream / pytorch.git / commit

author	Jongsoo Park <jongsoo@fb.com>
	Fri, 15 Feb 2019 17:44:32 +0000 (09:44 -0800)
committer	Facebook Github Bot <facebook-github-bot@users.noreply.github.com>
	Fri, 15 Feb 2019 17:50:11 +0000 (09:50 -0800)
commit	dad0dbd3b926b2729a5893758dc6f085b170d691
tree	c1531fb1b87a67a5a0ef2044812ccc6ed159bc32	tree \| snapshot
parent	90fc6133b2fed145536f3b479adf0e6f13fd9a6c	commit \| diff

merge fully_connected_rowwise_dnnlowp_op into fully_connected_dnnlowp_op (#17105)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/17105

To make FC with rowwise quantization faster, reduce code duplication, and make code consistent with Convolution

Reviewed By: csummersea

Differential Revision: D14080461

fbshipit-source-id: 2b0e67b86e7e3029c90751a8824bf80ae1223680

13 files changed:

caffe2/quantization/server/CMakeLists.txt		diff \| blob \| history
caffe2/quantization/server/conv_dnnlowp_op.cc		diff \| blob \| history
caffe2/quantization/server/conv_dnnlowp_op.h		diff \| blob \| history
caffe2/quantization/server/fbgemm_pack_matrix_cache.cc		diff \| blob \| history
caffe2/quantization/server/fbgemm_pack_matrix_cache.h		diff \| blob \| history
caffe2/quantization/server/fbgemm_pack_op.cc		diff \| blob \| history
caffe2/quantization/server/fbgemm_pack_op.h		diff \| blob \| history
caffe2/quantization/server/fully_connected_dnnlowp_acc16_op.cc		diff \| blob \| history
caffe2/quantization/server/fully_connected_dnnlowp_op.cc		diff \| blob \| history
caffe2/quantization/server/fully_connected_dnnlowp_op.h		diff \| blob \| history
caffe2/quantization/server/fully_connected_rowwise_dnnlowp_op.cc	[deleted file]	blob \| history
caffe2/quantization/server/fully_connected_rowwise_dnnlowp_op.h	[deleted file]	blob \| history
caffe2/quantization/server/fully_connected_rowwise_dnnlowp_op_test.py		diff \| blob \| history

Domain: Machine Learning / ML Framework;

RSS Atom