AI Workloads on Kubernetes: Scaling Smarter and Running Faster with k0rdent

Get started with k0rdent: https://docs.k0rdent.io/latest/quickstarts/ Access the k0rdent application catalog: https://catalog.k0rdent.io/v0.2.0/ With the rising adoption of AI technologies across industries, many are eager to see practical use cases in relation to Kubernetes. Deploying AI-powered workloads on top of Kubernetes can be complex, involving a lot of GPU provisioning, model serving/querying, and costly, time-consuming manual scaling steps. This webinar explores how to streamline AI deployments on Kubernetes using open source k0rdent and it's related components. Join Bharath Nallapeta, Sr. Software Engineer and Open Source Contributor at Mirantis, for a complete breakdown of AI and Kubernetes, in terms of usability, GPU access, and overall investment. He will also cover GPU monitoring strategies using Prometheus and Grafana (both integrate with k0rdent) to ensure optimal performance. With GPUs being both physically constrained and very costly, this session emphasizes how auto-scaling can maximize resource utilization while minimizing operational costs - all within one cohesive solution: k0rdent. Attendees of this webinar will learn: ⁃ How to automate GPU-ready cluster provisions with k0rdent ⁃ How to deploy scalable AI models with Kserve ⁃ How to optimize inference workloads using Knative & Istio ⁃ How k0rdent enhances flexibility, speed & scalability for AI-based Kubernetes 🚀 Join us to see how k0rdent empowers AI teams to deploy, scale, and optimize models effortlessly - ensuring maximum performance at the lowest cost. 🌐 k0rdent is open source and free. Learn more at https://k0rdent.io/ 🌐 Why k0rdent? Find out: https://www.mirantis.com/why-k0rdent/ 📑 Open Source Documentation: https://docs.k0rdent.io/latest/ #kubernetes #k8s #cloudnative #opensource #grafana #prometheus #istio #multicloud #multicluster 🖥️ For more on demand and upcoming webinars proctored by the teams at Mirantis, please visit: https://www.mirantis.com/cloud-webinars/ 📚 For more informative resources about Mirantis, our solutions and areas of expertise, please check out our resource library: https://www.mirantis.com/resources/ Learn more about Mirantis: https://www.mirantis.com/ Mirantis Enterprise Support: https://www.mirantis.com/support/enterprise-support-options/ Read the Mirantis Blog: https://www.mirantis.com/blog/ Cloud Native & Kubernetes Resources: https://www.mirantis.com/cloud-native-cookbook/ Mirantis Training: https://training.mirantis.com/ Questions? Contact us today: https://www.mirantis.com/contact/ CHAPTERS 0:00 - Intro & background on multi-cluster/multi-tenancy 2:22 - K8s necessitates platform engineering 5:57 - Multi-cluster/multi-cloud is the new norm 8:39 - Overview of open source k0rdent 11:45 - AI deployments w Kserve/Knative + AI Monitoring w Prometheus/Grafana 16:56 - k0rdent Demo pt1: AI workload cluster provisioning 26:32 - k0rdent Demo pt2: deploying AI/ML workloads 35:38 - Testing the Demo deployment 40:17 - Recap 43:04 - k0rdent application/infrastructure catalog 44:58 - Outro