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

Ignite

Deploying AI on Kubernetes sounds great—until you hit the reality of scalability bottlenecks, GPU resource struggles, and skyrocketing costs. This session tackles these challenges head-on, showcasing how k0rdent automates the entire AI infrastructure lifecycle to make AI workloads efficient, scalable, and cost-effective.

What You’ll See in Action:

  • Effortless Kubernetes Cluster Provisioning
    • Seamlessly spin up AI-ready clusters across clouds and on-prem with k0rdent.
  • GPU Acceleration, Minus the Hassle
    • Automate GPU setup with NVIDIA GPU Operator, ensuring smooth AI training and inference.
  • AI Model Deployment, the Smart Way
    • Expose models as scalable APIs using KServe, making AI inference easy.
  • Auto-Scaling That Saves You Money
    • Knative dynamically adjusts GPU resources—scaling up when needed, scaling to zero when idle.
  • Stay in Control with Proactive Monitoring
    • Track AI performance and GPU usage in real-time with Prometheus and Grafana.

Speaker

bharath-nallapeta

Bharath Nallapeta

 

Bharath Nallapeta is a seasoned cloud-native engineer specializing in Go, Kubernetes, and platform engineering. With extensive experience in designing and operating scalable Kubernetes infrastructure,

...