Strategies for Efficient LLM Deployments in Any Cluster
CNCF [Cloud Native Computing Foundation] via YouTube
Overview
Explore strategies for efficient Large Language Model (LLM) deployments in any cluster through this informative conference talk. Discover how to overcome challenges posed by LLMs' substantial size, resource demands, and management complexity in Kubernetes environments. Learn techniques to reduce model footprint, enabling deployment from cloud to edge. Gain insights on selecting the right model, reducing size, and optimizing resource utilization through WebAssembly. Understand the balance between resource usage and quality in LLM deployments. Stay updated on emerging technologies, projects, and models in this rapidly evolving ecosystem.
Syllabus
Strategies for Efficient LLM Deployments in Any Cluster -Angel M De Miguel Meana & Francisco Cabrera
Taught by
CNCF [Cloud Native Computing Foundation]