From Laptop to Cluster: Running AI Workloads Seamlessly from Podman... Ashley Cui & Urvashi Mohnani

This talk covers the development and deployment of AI workloads while bridging the gap between local environments and production Kubernetes. The speakers, Ashley Cui and Urvashi Mohnani from Red Hat, demonstrate a streamlined AI toolchain utilizing open source projects such as Podman, Ramalama, Kubernetes, and bootc. They showcase how to convert an AI model into a standard OCI image with Ramalama, test it locally using Podman, and manage containerized workloads. Additionally, the session includes using quadlet for container orchestration under systemd and deploying the AI application from development to a production-ready state in a Kubernetes environment. A highlight is the exploration of bootc, which enables consistent application execution across various environments, including clusters and edge devices.