Join us for an immersive virtual hands-on workshop exploring how to build and scale production-ready Generative AI deployments on Amazon EKS using NVIDIA GPUs. Learn how to deploy and manage production-grade LLM workloads, implement advanced RAG patterns with vector databases, and leverage open-source frameworks for data-backed LLM applications. Through hands-on labs, you'll gain best practices for deploying, scaling, and observing Gen AI inference workloads on Kubernetes. Whether you're deploying your first language model or scaling existing workloads, this workshop provides the tools and experience you need. 

What You Will Learn 

• How to set up an Amazon EKS cluster optimized for NVIDIA GPU workloads 
• Infrastructure options for running AI/ML workloads on Amazon EKS 
• Efficient model serving and scaling using vLLM 
• Distributed inference architecture implementation with Ray 
• Observability for vLLM and Ray using Prometheus and Grafana 
• Best practices for production Gen AI deployments on Kubernetes