Scaling LLM Applications on Arm: Optimize for Performance and Cost in the Cloud

Running cloud workloads and containerized LLM-based applications on Arm delivers better price-performance, improves energy efficiency, and meets growing demands for scale and sustainability. In this hands-on workshop, get a walkthrough of the end-to-end process of containerizing a PyTorch application, building multi-architecture Docker images, deploying Azure Kubernetes Service (AKS) using Terraform, and running your application across scalable cloud workloads. If you’re running applications in the cloud, this session shows you how to do it better, faster, and more cost-effectively.

All workshop attendees are required to bring their own laptop