Ollama on Kubernetes : How to Deploy Ollama on Kubernetes

Join Mike Peterson as he dives into a practical, hands-on demo showcasing how to deploy Ollama on Kubernetes using vCluster to create a cost-effective, multi-tenant environment. In this session, Mike will demonstrate how to set up virtual clusters that provide isolated Kubernetes environments running on shared infrastructure, enabling efficient GPU usage for multiple users.

Date & time: September 11, 5:30 PM
Location: Online (Teams Webinar)
Presented by: Mike Peterson, Senior Technical Marketing Engineer at vCluster.

Attendees will learn:

• How to deploy Ollama in a virtual cluster on Kubernetes
• Setting up GPU runtime classes for optimized GPU sharing
• Creating deployments, services, and ingress resources for Ollama
• Connecting and interacting with Ollama running inside the Kubernetes cluster using the Ollama client on a local machine
• Tips on multi-tenancy, managing costs, and securing access with OAuth techniques

This webinar is perfect for cloud-native developers and platform engineers interested in managing AI workloads efficiently on Kubernetes while minimizing costs. Join to see how vCluster enables scalable, secure, and cost-effective deployments of AI models with practical insights and live demonstrations.

Connect With Us on Social Media

Instagram: https://www.instagram.com/torontoai_
Facebook: https://www.facebook.com/profile.php?id=100068811921154
LinkedIn: https://www.linkedin.com/company/torontoai/
TikTok: https://www.tiktok.com/@torontoai_?_t=zs-8yvjfept7ob&_r=1