onnxruntime/onnxruntime
ytaous cb2dfee31c
Size Op - CUDA kernel support (#4868)
* cuda kernel support

* on comments

* test UT

* test UT

* revert settings

* attempt to fix broken UT

* corrected UT fix

Co-authored-by: Ethan Tao <ettao@microsoft.com>
2020-08-25 14:26:41 -07:00
..
contrib_ops Reduce ONNX dependency in minimal build (#4890) 2020-08-23 07:02:13 +10:00
core Size Op - CUDA kernel support (#4868) 2020-08-25 14:26:41 -07:00
featurizers_ops/cpu Initial checkin (#3791) 2020-05-01 14:58:49 -07:00
gsl Fix static analysis warnings found by VC++ (#3530) 2020-04-16 01:46:47 -07:00
python Export GPT-2 ONNX model without postion_ids and attention_mask inputs (#4852) 2020-08-24 13:05:25 -07:00
test Support double for ArgMax operator (#4907) 2020-08-25 13:23:52 -07:00
tool/etw Fix static analysis warnings found by VC++ (#3530) 2020-04-16 01:46:47 -07:00
.style.yapf Enable running PEP8 on python scripts using flake8 (#3928) 2020-05-15 07:15:06 +10:00
__init__.py Add new PytTrch front-end (#4815) 2020-08-17 09:45:25 -07:00
ReformatSource.ps1
ReformatSourcePython.bat Update GPT2 Model Benchmark Script to Support IO Binding (#4088) 2020-06-01 15:07:48 -07:00
VSCodeCoverage.runsettings