Content

Intended scenario: AI model inference. Features: Service deployment by using an image: You can quickly deploy an AI inference service by configuring a preset image and third-party code library, mounting models and code, and running commands. AI-Web application deployment by using an image: You quickly deploy an AI-Web application and start a web application, such as gradient, flask, and SDwebUI. Service deployment by using model and processor: You can use the preset processors provided by Machine Learning Platform for AI (PAI) to quickly deploy services. The processors are suitable for various model frameworks, such as PMM and XGBOOST.