Azure Container Apps makes it easier than ever to build and run modern AI-powered applications. Whether you're running AI inference or fine-tuning AI models, this fully managed platform simplifies workload management and scaling, removing operational complexity.

In this session, we’ll show you how to leverage serverless GPUs to run text generation and embedding inference endpoints in Azure Container Apps. You’ll learn how to secure and scale your serverless AI solution while running different models through a single, standardized interface.