What we’re about
vLLM is a high-throughput, memory-efficient open-source library for fast LLM inference and serving, widely used for deploying large language models in production.
This meetup group is for anyone curious about how LLM inference works—and eager to learn the state-of-the-art techniques that power it.
Whether you're a developer, researcher, or just getting started with AI, you're welcome to join us in Hong Kong to explore vLLM, share insights, and connect with others.
Upcoming events
No upcoming events
