onnxruntime/onnxruntime
pengwa 9959e84906
Gelu fusion - kernel and transformer (#1746)
* Gelu contrib op & transformer

* Gelu kernels for CPU&cuda

* Merged PR 5034: fix a condition for gelu transformer

The ONNX models doesn't guarantee to assign an unique name to each node, so the previous condition could fail.

(cherry picked from commit e335ef5466444cb0aae45f885ea3a825ed9f1088)

* Fix builds

* remove useless comments

* fix test failure when nocontribp

* Move impelmentation under KMSdomain

* fix comments

* fix linux build

* Fix few comments

* fix linux build
2019-10-03 19:34:46 +08:00
..
automl_ops Implement C API entry points for creating and fetching non-standard types to OrtValue (#1714) 2019-09-11 14:52:47 -07:00
contrib_ops Gelu fusion - kernel and transformer (#1746) 2019-10-03 19:34:46 +08:00
core Gelu fusion - kernel and transformer (#1746) 2019-10-03 19:34:46 +08:00
gsl Replace GSL with GSL-LITE submodule and fix up refs (#1920) 2019-10-01 12:43:29 -07:00
python python session.run() fallback to CPU/CUDA provider for EP failures. (#1960) 2019-10-02 02:38:03 -07:00
server Replace GSL with GSL-LITE submodule and fix up refs (#1920) 2019-10-01 12:43:29 -07:00
test Gelu fusion - kernel and transformer (#1746) 2019-10-03 19:34:46 +08:00
__init__.py logging related fixes. (#1930) 2019-09-25 23:48:23 -07:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings