Tianlei Wu comments

Results 110 comments of


                                            Tianlei Wu

trafficstars

[Performance] Regression observed when using CUDA execution provider

I reproduced the issue with https://github.com/onnx/models/blob/main/validated/vision/classification/resnet/model/resnet50-v1-12.onnx in A100. The average latency (ms) output: ORT 1.13.1: 2.98 ORT 1.14.0: 3.20 ORT 1.17.1: 3.20 So there is some regression from 1.13.1 to...

[Performance] Regression observed when using CUDA execution provider

The root cause seems to be the change of default value of cudnn_conv_use_max_workspace from 0 to 1 in https://github.com/microsoft/onnxruntime/pull/13981. The solution is to set the value to 0 for Resnet:...

[Performance] Regression observed when using CUDA execution provider

@gedoensmax, The Nsight trace files: [resnet_nsys.zip](https://github.com/user-attachments/files/15540225/resnet_nsys.zip)

[WIP] Contrib operator for Deformable Multi-Scale Attention

/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal...

[WIP] Contrib operator for Deformable Multi-Scale Attention

/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

[CUDA EP] Fix BeamSearch on T5 with sequence_as_input_ids (#20667)

/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows GPU TensorRT CI...

[CUDA EP] Fix BeamSearch on T5 with sequence_as_input_ids (#20667)

/azp run Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-linux-gpu-ci-pipeline,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Linux Android Emulator QNN CI Pipeline,Android CI Pipeline

[CUDA EP] Fix BeamSearch on T5 with sequence_as_input_ids (#20667)

/azp run iOS CI Pipeline,ONNX Runtime React Native CI Pipeline,CoreML CI Pipeline,Linux DNNL CI Pipeline,Linux MIGraphX CI Pipeline,Linux ROCm CI Pipeline