Yufeng Li comments

Results 73 comments of


                                            Yufeng Li

[mlas] Speed up tanhf activation function

/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Android CI Pipeline

[mlas] Speed up tanhf activation function

/azp run ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux GPU CI Pipeline,orttraining-amd-gpu-ci-pipeline,Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline

[mlas] Speed up tanhf activation function

/azp run Linux Android Emulator QNN CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU TensorRT CI Pipeline, Windows ARM64 QNN CI Pipeline, Windows CPU CI Pipeline ,...

[mlas] Speed up tanhf activation function

You need sign the license/cla agreement to move on.

[mlas] Speed up tanhf activation function

/azp run ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux GPU CI Pipeline,orttraining-amd-gpu-ci-pipeline,Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline

[mlas] Speed up tanhf activation function

/azp run Linux Android Emulator QNN CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU TensorRT CI Pipeline, Windows ARM64 QNN CI Pipeline, Windows CPU CI Pipeline ,...

[mlas] Speed up tanhf activation function

> @yufenglee Couple of questions I need help with: > > 1. I'm unable to replicate the `Windows CI pipeline` run fail locally (fail log [here](https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=1382352&view=logs&j=2c350baf-0cef-5ef1-cbeb-e5cd88c89a11&t=e2851d88-2248-5227-ac0b-d999486a4bf5)). The test `LSTMTest.BackwardCompute` passes...