ONNX Runtime is a high-performance inference engine for deploying ONNX models to production. It's optimized for both cloud and edge and works on Linux, Windows, and Mac. Written in C++, it also has C, Python, C#, Java, and JavaScript (Node.js) APIs for usage in a variety of environments. ONNX Runtime supports both DNN and traditional ML models and integrates with accelerators on different hardware such as TensorRT on NVidia GPUs, OpenVINO on Intel processors, DirectML on Windows, and more. By using ONNX Runtime, you can benefit from the extensive production-grade optimizations, testing, and ongoing improvements.

You will Learn how using the Open Neural Network Exchange (ONNX) can help optimize the inference of your machine learning model. Inference, or model scoring, is the phase where the deployed model is used for prediction, most commonly on production data.

AI-102 Certification course

• Get ONNX models
• Deploy ONNX models in Azure
• Install and use ONNX Runtime with Python

https://learn.microsoft.com/training/courses/ai-102t00