19 Commits (8645591d664f9e059113900281a715f8f83ae93c)

Author	SHA1	Message	Date
mapingshuo	7d4002e06a	restrict block num of layer_norm_grad cuda block to 128 (#23878) ... restrict block num of layer_norm_grad cuda kernel to 128, test=develop	5 years ago
Pei Yang	0a51098a71	Add TRT support for BERT (#21135) ... * add gelu plugin * align trt bert with gpu * add support for fused fc with relu, * add unittest for bert trt	5 years ago
Yihua Xu	69dd5152cf	Fix the crash issue when scale or bias was null-pointer. (#21284) ... * Fix the crash issue when scale or bias was null-pointer. test=develop * Add the error message for passing CI. test=develop	5 years ago
danleifeng	0e7baabe59	extend elementwise broadcast function (#20957)	5 years ago
sneaxiy	023a3a3d62	fix op grad maker ... test=develop	6 years ago
tensor-tang	14a764c930	simplify the jitkernel templates and tests ... test=develop	6 years ago
tensor-tang	802f362ac4	unify the kernelfuncs cache and add unit test ... test=develop	6 years ago
tensor-tang	1aaec571c2	fix enum style ... test=develop	6 years ago
tensor-tang	6648995f53	fix build	6 years ago
tensor-tang	720b55cbcf	enable crf decoding and layer norm refer code	6 years ago
Yihua Xu	f4c869d872	Optimize the layer_norm operator with AVX intrinsic function (#14417) ... * Optimize layer_norm operator with AVX intrinsic functions * Revert the wrong modifications * Implement the jit kernel for layer_norm operator * Add math headfile to fix the compile issue (test=develop) * Add math headfile to fix the compile issue (test=develop) * Fixed the intrinsic headfile issue (test=develop) * Fix the conflicts (test=develop) * Revert for CUDA compiler (test=develop) * Fixed the cuda depency (test=develop) * Fix the marco issues (test=develop)	6 years ago
Wu Yi	a2d9b34417	Refine operator cmake (#14413) ... * wip simplify operator framework * wip * wip * done test=develop * clean test=develop * fix test=develop * fix deps test=develop * fix cpu build test=develop * fix tensorrt build test=develop * fix tests test=develop * fix test=develop * fix cpu build test=develop	6 years ago
Yu Yang	ef6ea790dc	Clean and extract blas	7 years ago
Xin Pan	1a4be55a47	Pass cpu build	7 years ago
Xin Pan	904fa05f46	Improve layer_norm speed ... transfomer on a single device step time reduces from 0.157 to 0.125	7 years ago
Yi Wang	cfffb1a362	Update tensor_util.h (#8422) ... * Update tensor_util.h * Update with moved TensorDesc * Fix tensur_utils.cu * Update * Update * Update * Update * Make tensor_util.cu a symbolic link	7 years ago
qingqing01	24509f4af9	Fix the grammar in copyright. (#8403)	7 years ago
Yi Wang	fc374821dd	Correct #include path	7 years ago
Yi Wang	90648f336d	Move file to fluid/; Edit CMakeLists.txt	7 years ago