Microsoft's Windows ML 2.0 aims to be the DirectX of AI development, allowing models to run seamlessly across any Windows PC hardware without developers needing to worry about compatibility issues.

The New Stack is a publication covering trends and technologies in cloud-native development, DevOps, and software delivery. Developers can learn about containerization, Kubernetes, and cloud computing, as well as explore topics such as microservices architecture, serverless computing, and continuous integration/continuous delivery (CI/CD) pipelines.

The New Stack

Microsoft announced Windows ML 2.0, an AI runtime designed to be the DirectX equivalent for AI development on Windows PCs. The technology aims to solve hardware compatibility issues by allowing AI models to run seamlessly across different hardware configurations including CPUs, GPUs, and NPUs from Intel, AMD, and NVIDIA. Built on the ONNX runtime, Windows ML 2.0 automatically handles hardware detection, dependency management, and performance optimization, eliminating the need for developers to create multiple versions for different hardware. The experimental version is currently available for testing, with Microsoft positioning it as a solution to simplify AI app development on Windows platforms.

Microsoft Targets AI ‘Holy Grail’ With Windows ML 2.0