Zhang Lei 24016a517b Prepacking in Gemm with merged logic for Matmul and Gemm on PackingB. (#5693) ... Prepacking in Gemm with merged logic for Matmul and Gemm on PackingB.		2020-11-05 22:35:24 -08:00
..
codegen	Add ability to filter GraphViewer using IndexedSubGraph. (#5614)	2020-11-04 07:08:18 +10:00
common	ThreadPool clean up : mm_pause in loops, correctly spin-then-wait, and adopt static methods consistently in the API (#5590)	2020-10-28 09:49:18 +00:00
dll
flatbuffers	Support for Sparse Initializers (#5540)	2020-10-27 10:32:06 -07:00
framework	Partition full graph one execution provider at a time (#5635)	2020-11-06 07:26:00 +10:00
graph	The IndexedSubGraph is used to create the Function body, but after that is invalid as the nodes it referred to have been removed from the main Graph. As such there's no need to store it in the FunctionImpl instance. (#5669)	2020-11-05 17:21:56 +10:00
language_interop_ops	Change the OrtCustomOp invocation as a constant. (#5506)	2020-11-02 10:38:07 -08:00
mlas	optimize QLinearConv depthwise convolutions (#5605)	2020-10-28 16:42:53 -07:00
optimizer	Dropout op elimination - enable for ORT training (#5588)	2020-10-27 11:51:23 -07:00
platform	Loosen tolerance of CudaKernelTest.ReduceSum_MidTensor, allow test random seed to be regenerated within a test run. (#5675)	2020-11-03 10:37:00 -08:00
profile
protobuf	implement per-channel for quantizelinear and dequantizelinear (#4759)	2020-08-21 12:08:50 -07:00
providers	Prepacking in Gemm with merged logic for Matmul and Gemm on PackingB. (#5693)	2020-11-05 22:35:24 -08:00
session	Remove redundant const_cast (#5705)	2020-11-05 09:43:22 -08:00
util	Implement Im2colNd NHWC and related qlinearconv logic for u8s8. (#5612)	2020-10-30 15:28:30 -07:00