Scott McKay 6cc57721f4 Change CUDA implementation of Transpose to support all fixed size tensor types (#2387) ... * Change CUDA implementation of Transpose to not use a typed kernel so we can support more types with minimum binary size. Add support for 8, 16, 32 and 64 bit types. Add unit tests. Add method so the implementation can be called directly (will be used by CUDA Scan very soon). * Disable TensorRT for MLFloat16 and int8 unit tests. * Address PR comment and add support for calling cublas implementation if type is mlfloat16.		2019-11-15 10:36:28 +10:00
..
automl_ops	Fix kernel registry bug (#2137)	2019-10-17 23:10:54 -07:00
contrib_ops	Fuse Add + Gelu (#2360)	2019-11-13 09:26:00 -08:00
core	Change CUDA implementation of Transpose to support all fixed size tensor types (#2387)	2019-11-15 10:36:28 +10:00
gsl	Downgrade compiler to CentOS 4.8.5 (#1985)	2019-10-03 15:40:46 -07:00
python	Direct use python numpy array's memory if already contiguous. (#2355)	2019-11-11 13:46:55 -08:00
server	Openvino EP R3.1 onnxrt server (#2357)	2019-11-11 12:22:19 -08:00
test	Change CUDA implementation of Transpose to support all fixed size tensor types (#2387)	2019-11-15 10:36:28 +10:00
tool/etw	Add Tracelogging for profiling (#1639)	2019-11-11 21:34:10 -08:00
__init__.py	Update version number	2019-10-30 08:13:09 -07:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings