Deploy LLM models efficiently and at scale with serverless containers

Description

More and more, organizations are looking to start deploying LLM models to solve for a variety of business use cases. In this session, review the various infrastructure options and integrations that can help you deploy LLM models using Amazon ECS: CPU inference, Amazon ECS with AWS Fargate, accelerated inference with GPU and Inf1, Amazon ECS on Amazon EC2, and associated storage and networking options.