VLLM

The raffle for a Lime Green Game Boy is still open! 🍋‍🟩🎮
The rules: ✅ 1 entry per invite sent ✅ 2 entries per invite who shows up in person!

vLLM is used to deploy production-scale inferencing systems into Cloud Native environments. In this session, we will explore how vLLM operates in a Kubernetes environment, integration points for the vLLM engine, and explores orchestration and operational lifecycles required to scale inference effectively.”