Catalog

Some of the most innovative AWS customers are using Amazon EKS to train, fine-tune, and serve cutting-edge generative AI models. In this workshop, learn how to serve fine-tuned models with vLLM and Ray Serve for a high-performance solution and be cost effective with Karpenter for right-sized accelerated compute. Through real-world, hands-on examples, learn some key patterns that can help you implement LLMOps for scaling inference workloads, integrating RAG frameworks, and optimizing performance within the Kubernetes ecosystem. You must bring your laptop to participate.