Du Li 621b3ac03a FFT contrib ops (#3381) ... * add custom op skeleton * Adding Rfft, Irfft kernels. * Fix a few errors: 1. make kernel stateless to avoid race condition 2. reclaim cufft plan * Adding MLFloat16 support * Adding fp16 support for fft ops. * Adding cufft plan cache. * adding a util func * adding copyright info. * Accommodating PR comments.		2020-04-14 10:12:04 -07:00
..
activation	Replacing CudaAsyncBuffer with TArray to improve perf (#3303)	2020-03-24 12:13:27 -07:00
bert	Change mask_index input of Attention op to be optional (#3459)	2020-04-12 22:55:37 -07:00
math	FFT contrib ops (#3381)	2020-04-14 10:12:04 -07:00
tensor	move all contrib ops to contrib ops namespace (#1190)	2019-06-24 10:19:01 -07:00
conv_transpose_with_dynamic_pads.cc
conv_transpose_with_dynamic_pads.h
layer_norm.cc	Revert an op version change (#3026)	2020-02-18 09:43:18 -08:00
layer_norm.h	Add layernorm operator (#1967)	2019-10-03 11:32:13 -07:00
layer_norm_impl.cu	use cublasHgemm for Volta GPU (#2074)	2019-10-14 17:29:13 -07:00
layer_norm_impl.h	Add layernorm operator (#1967)	2019-10-03 11:32:13 -07:00