As you advance in your journey from evaluating foundation models (FMs) to building generative AI applications at scale, you need services to deploy these models at the best price performance. From low latency (a few milliseconds) and high throughput (millions of transactions per second) use cases for chatbots to long-running inference use cases for natural language processing, you can use Amazon SageMaker for virtually all your inference needs.

In this session, take a deep dive tour of features that make SageMaker a great choice for deploying FMs for inference and learn how you can benefit from AWS innovations.