Tianlei Wu 7b39f5090c Add Attention op for multi-head self attention in BERT (#1984) ... * Add Attention op for multi head self attention in BERT * Add test cases * Move op from kOnnxDomain to kMSDomain. Limit test to run by CUDA provider only. * fix test * Add float16 test * fix cpu build error * handle cuda error * get last cuda error when failed		2019-10-07 12:22:54 -07:00
..
automl/featurizers/src/FeaturizerPrep	Downgrade compiler to CentOS 4.8.5 (#1985)	2019-10-03 15:40:46 -07:00
codegen	Bumped up to op_ver 11 for a bunch of Nuphar Ops (#2025)	2019-10-07 10:34:05 -07:00
common	Weba/merge ngemm (#2021)	2019-10-05 12:09:22 -07:00
framework	Resort to sequential execution if the inter op thread pool ptr is nullptr; (#2023)	2019-10-06 16:08:41 -07:00
graph	Add Attention op for multi-head self attention in BERT (#1984)	2019-10-07 12:22:54 -07:00
language_interop_ops	Ryanunderhill/api interface (#1855)	2019-09-20 13:39:11 -07:00
mlas	use mlaserf (#1999)	2019-10-04 15:17:26 -07:00
optimizer	Update TensorRT to version 6.0.1.5 (#1966)	2019-10-06 10:40:53 -07:00
platform	Replace GSL with GSL-LITE submodule and fix up refs (#1920)	2019-10-01 12:43:29 -07:00
protobuf	Bump up ONNX to the latest commit (#1868)	2019-09-20 18:15:16 -07:00
providers	Bumped up to op_ver 11 for a bunch of Nuphar Ops (#2025)	2019-10-07 10:34:05 -07:00
session	Fix logger regression (#2011)	2019-10-04 16:39:40 -07:00
util	Downgrade compiler to CentOS 4.8.5 (#1985)	2019-10-03 15:40:46 -07:00