Dmitri Smirnov 3433576fd3 Support for Sparse Initializers (#5540) ... Introduce sparse_initializers support. Convert them to dense on model load and prune graph_proto_ so they don't consume space. Convert back to sparse on ORT Format model save. Implement serializing sparse initializers to OrtFormat. Fix Model::ToProto() to return original sparse initializers Set a flag that graph_sync is needed when loading a simple ORT Format model. otherwise nothing is resolved. Add ORT Format history to README.md ifdef MINIMAL build for DenseToSparseTensorInitializer Allow duplicate initializers to support existing models. Issue a warning instead of aborting. * Revert "Remove SparseTensor support from minimal build. (#5114)" This reverts commit 59ee8ffb17. Signed-off-by: Dmitri Smirnov <dmitrism@microsoft.com>		2020-10-27 10:32:06 -07:00
..
contrib_ops	GatherGrad optimization (#5524)	2020-10-26 12:53:53 -07:00
core	Support for Sparse Initializers (#5540)	2020-10-27 10:32:06 -07:00
featurizers_ops/cpu
gsl
python	Attention with past and no unidirectional mask (#5557)	2020-10-21 20:12:02 -07:00
test	Support for Sparse Initializers (#5540)	2020-10-27 10:32:06 -07:00
tool/etw	Add option ORT_NO_EXCEPTIONS to disable most exception/throw in /onnxruntime/ (#4894)	2020-08-28 23:03:51 -07:00
.style.yapf
__init__.py	[C# and Python APIs] Expose knobs to enable/disable platform telemetry collection (#5481)	2020-10-21 10:32:13 -07:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings