microsoft
[WIP] Contrib operator for Deformable Multi-Scale Attention
Description
Introduce a contrib operator for Deformable Multi-Scale Attention
Motivation and Context
Deformable Multi-Scale Attention is first proposed in Deformable DETR. Implementing it with official ONNX operators results in poor performance on CPU. We implemented with AVX-512 intrinsics and the performance improved ~20x with the same input size. Note that our optimized implementation only works for certain parameter values.
/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 Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline
/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
![azure-pipelines[bot] avatar](https://avatars.githubusercontent.com/in/9426?v=4 "Published by a pub.dev verified publisher"){kind=small}
/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 Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline
/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