Video by CNCF [Cloud Native Computing Foundation] via YouTube

Qianru Lao of OpenAI explores proxy/controller patterns for routing LLM inference across Kubernetes clusters, accelerator-backed engines, changing demand and geographic regions.
Join us November 9-12 in Salt Lake City.
Explore the Session: https://bit.ly/4Bcn843
Join us! https://bit.ly/3BDI5XL