You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Yiqun Liu a65c728e5d Implement the GPU kernel of fc operator (#19687) ... * Refine the codes related to fc op. * Add GPU implementation for fc functor. * Apply fc_fuse_pass in GPU inference. test=develop * Change the cmake for fc op. * Change PADDLE_ENFORCE to PADDLE_ENFORCE_EQ. * Add an attribute to set the activation type in fc_op. * Enhance the unittest of fc_op. test=develop * Remove the declaration of FCOpGrad back to the header file. test=develop * Set default value for newly added arguments in test_fc_op. test=develop		6 years ago
..
anakin	paddle::framework::vectorize() templatization [PART3] (#19643)	6 years ago
analysis	Enable ngraph through build_strategy (#19266)	6 years ago
api	Implement the GPU kernel of fc operator (#19687)	6 years ago
tensorrt	paddle::framework::vectorize() templatization [PART3] (#19643)	6 years ago
tests	A a pass to enable the use of cudnn (#19346)	6 years ago
utils	Merge branch 'develop' of https://github.com/paddlepaddle/paddle into HEAD	6 years ago
CMakeLists.txt	[WIP] Add Imdb train demo (#18895)	6 years ago
check_symbol.sh	Cherry-pick benchmark related changes from release/1.4 (#17156)	6 years ago
engine.h	add static model load for trt	6 years ago
io.cc	load persistables with selected rows, test=develop (#17047)	6 years ago
io.h	update with comments	6 years ago
paddle_fluid.map	inference_shared_library support profile (#16275)	6 years ago
paddle_fluid.sym	paddle fluid static lib symbol hidden	7 years ago