The Fast and the Curious - Chasing Scalable AI Dreams with Kubernetes and k0rdent

Learn how to deploy AI at scale on Kubernetes through this 14-minute conference talk that addresses the complex challenges of GPU provisioning, cost management, and performance optimization. Discover how k0rdent automates GPU-ready cluster provisioning to make AI deployment seamless across both cloud and on-premises environments. Explore techniques for serving AI models with KServe, implementing dynamic GPU resource scaling with Knative auto-scaling, and monitoring performance using Prometheus and Grafana. Master strategies for maximizing compute efficiency while minimizing costs in an environment where GPUs are both scarce and expensive. Follow along with a live demonstration that walks through the complete AI deployment workflow, from spinning up clusters to running real-time inference, and gain practical insights into streamlining AI operations with Kubernetes without the typical complexity.