AI on Kubernetes: Scaling Smarter, Running Faster with k0rdent

Logo
Presented by

Bharath Nallapeta, Senior Software Engineer & Open Source Contributor

About this talk

Deploying AI on Kubernetes can be complex, involving GPU provisioning, model serving, and cost-efficient scaling. This session explores how to streamline AI deployments on Kubernetes using k0rdent. Attendees will learn how to automate GPU ready cluster provisioning, deploy scalable AI models with Kserve, and optimize inference workloads with Knative and Istio. With GPUs being constrained and costly, this session emphasizes how auto-scaling can maximize resource utilization while minimizing operational costs. The talk will also cover GPU monitoring strategies using Prometheus and Grafana to ensure optimal performance. Join us to see how k0rdent empowers AI teams to deploy, scale, and optimize models effortlessly—ensuring maximum performance at the lowest cost.
Related topics:

More from this channel

Upcoming talks (2)
On-demand talks (119)
Subscribers (14792)
Mirantis helps organizations ship code faster utilizing public and private clouds, providing a public cloud experience on any infrastructure from the data center
to the edge. With a long-standing record of delivering solutions based on open source with enterprise-grade support, Mirantis offers an as-a-service
experience of Kubernetes and OpenStack to provide containerization and virtualization services. Mirantis serves many of the world’s leading enterprises,
including Adobe, DocuSign, Liberty Mutual, Nationwide Insurance, Reliance Jio, S&P Global, Seagate, Société Générale, and Volkswagen. Learn more at www…