Ye Wang 803837df63 Add 4dmask support for attention cuda kernel (#7591) ... * checkin * add 4dmask support in attention cuda op * trim * add comments * fix build/test error * review comments and add tests * sync doc * review comments * minor change		2021-05-07 20:17:29 -07:00
..
activation	Support to allow user to specify compute stream per session (#3723)	2021-02-05 15:48:18 -08:00
bert	Add 4dmask support for attention cuda kernel (#7591)	2021-05-07 20:17:29 -07:00
math	Change onnxruntime::make_unique to std::make_unique (#7502)	2021-04-29 17:04:53 -07:00
quantization	Support larger hidden size in Attention Cuda kernel (#7002)	2021-03-15 15:46:10 -07:00
tensor	Support to allow user to specify compute stream per session (#3723)	2021-02-05 15:48:18 -08:00
conv_transpose_with_dynamic_pads.cc
conv_transpose_with_dynamic_pads.h
cuda_contrib_kernels.cc	Promote BiasDropout from orttraining to onnxruntime (#7116)	2021-03-24 20:42:42 -07:00
cuda_contrib_kernels.h	move cpu/cuda related files to coresponding cpu/cuda folder (#3668)	2020-04-24 00:12:02 -07:00
fused_conv.cc	Move constants from heap to stack to avoid randomness on cudnn function (#6869)	2021-03-03 20:18:21 -08:00
inverse.cc	Change onnxruntime::make_unique to std::make_unique (#7502)	2021-04-29 17:04:53 -07:00
layer_norm.cc	Support no bias in layernorm and skiplayernorm op (#6554)	2021-02-05 16:48:22 -08:00
layer_norm.h	Reduce amount of compiled CUDA device code (#6118)	2020-12-14 15:27:40 -08:00
layer_norm_impl.cu	Add function body to LayerNorm (#7378)	2021-04-28 09:31:53 -07:00
layer_norm_impl.h	Support to allow user to specify compute stream per session (#3723)	2021-02-05 15:48:18 -08:00