onnxruntime/include
Tianlei Wu e57b735bb9 Add a transformer to use Gelu approximation for cuda provider (#2480)
* Add Gelu Approximation Transformer to convert Gelu or AddGeluFusion to FastGelu to get better inference performance.
2019-11-27 10:15:50 -08:00
..
onnxruntime/core Add a transformer to use Gelu approximation for cuda provider (#2480) 2019-11-27 10:15:50 -08:00