Ramakrishnan Sivakumar 5bcb5f5a3d MLAS: Add support for AVXVNNI (#5592) ... Adds Gemm kernels with AVXVNNI support for Int8 acceleration		2020-10-26 16:27:48 -07:00
..
codegen	Convert TensorRT provider into a shared library (#4721)	2020-08-10 21:17:16 -07:00
common	Sunghcho/denormals (#5391)	2020-10-15 12:47:42 -07:00
dll
flatbuffers	Add #include for std::tolower. Fixes VS2017 build error. (#5544)	2020-10-20 18:00:57 +10:00
framework	NVTX label change (#5562)	2020-10-22 10:34:20 -07:00
graph	Add alternate IsSupportedOptypeVersionAndString signature (#5529)	2020-10-18 18:14:06 -07:00
language_interop_ops	Changes to enable saving and loading an ORT format model (#4995)	2020-09-03 09:10:48 -07:00
mlas	MLAS: Add support for AVXVNNI (#5592)	2020-10-26 16:27:48 -07:00
optimizer	Enable CommonSubexpressionElimination in training. (#5504)	2020-10-26 11:25:15 -07:00
platform	Sunghcho/denormals (#5391)	2020-10-15 12:47:42 -07:00
profile
protobuf	implement per-channel for quantizelinear and dequantizelinear (#4759)	2020-08-21 12:08:50 -07:00
providers	GatherGrad optimization (#5524)	2020-10-26 12:53:53 -07:00
session	Bug fix for C API (#5520)	2020-10-24 13:37:58 -07:00
util	Remove MKLML build config (#5559)	2020-10-21 13:11:25 -07:00