Session: llm-d: Open Source Infrastructure for Cost-Efficient LLM Deployment at Scale

How do you deploy LLMs efficiently when a single model can cost millions in compute? Learn how llm-d, an open source Kubernetes-native platform, solves enterprise LLM deployment challenges through intelligent scheduling, resource optimization, and community-driven innovation. This talk covers real-world deployment patterns, cost reduction strategies, and how to contribute to the project.