The explosion of interest in Generative AI has brought to light the critical need for scalable and reliable infrastructure to support these advanced technologies. Foundational models driving generative AI, particularly those used in commercial platforms like OpenAI, rely heavily on Kubernetes for model serving and inference endpoints.

This session delves into the practical aspects of deploying open-source generative AI models and applications within a Kubernetes and cloud-native framework. A key focus will be on how enterprises can establish end-to-end pipelines to develop context-rich, Large Language Model (LLM)-based applications in-house. This approach is particularly beneficial for handling sensitive data securely, without the need to rely on external endpoints.

Designed for those seeking to understand the intersection of modern AI and cloud-native technology, this hands-on session will share insights and best practices for running cutting-edge AI applications on Kubernetes. Attendees will leave with a deeper understanding of how to harness the power of Kubernetes to optimize their generative AI projects.