Scaling Generative AI Inference with llm-d

Learn how to deploy and serve large generative AI models in production at scale using llm-d, an open-source, Kubernetes-native distributed inference serving stack. Explore the significant challenges of deploying large generative AI models in production environments and discover how llm-d provides streamlined solutions for developers. Understand llm-d's architecture and key features that enable fast time-to-value and competitive performance across diverse hardware accelerators. Gain practical knowledge about leveraging tested and benchmarked recipes for production deployments, with a focus on real-world applications and industry best practices for scaling generative AI inference systems.