Generative AI on Kubernetes, Inside the Infrastructure Behind AI at Scale

Building generative AI is one challenge. Running it reliably at scale is another. In this discussion, Red Hat Distinguished Engineers Daniele Zonca and Roland Huß explore Generative AI on Kubernetes, an ebook that focuses on the infrastructure and operational challenges of deploying large language models (LLMs) on Kubernetes.

Rather than solely explaining how to build AI models, the book is written for MLOps professionals and platform engineers responsible for operating AI at scale. The conversation covers GPU scheduling, ML Ops, platform engineering, security and operating production AI workloads on Kubernetes.

Learn more and download the book at no-cost: https://red.ht/genaionkubernetes