KubeCon + CloudNativeCon North America 2024

In this session, we'll cover best practices for deploying, scaling, and managing LLM inference pipelines on Kubernetes (K8s). We'll explore common patterns like inference, retrieval-augmented generation (RAG), and fine-tuning. Key challenges addressed include: [1]. Minimizing initial inference latency with model caching [2] Optimizing GPU usage with efficient scheduling, multi-GPU/node handling, and auto-quantization [3] Enhancing security and management with RBAC, monitoring, auto-scaling, and support for air-gapped clusters We'll also demonstrate building customizable pipelines for inference, RAG, and fine-tuning, and managing them post-deployment. Solutions include [1] a lightweight standalone tool built using operator pattern and [2] KServe, a robust open-source AI inference platform. This session will equip you to effectively manage LLM inference pipelines on K8s, improving performance, efficiency, and security