Shanghai vLLM Meetup with Red Hat and MetaX

​We are excited to invite you to the vLLM meetup in Shanghai, China, hosted by Red Hat and MetaX.

​​This is your chance to connect with a growing community of vLLM users, developers, maintainers, and engineers from Red Hat. We'll dive deep into technical talks, share insights, and discuss our journey in optimizing LLM inference for performance and efficiency.

Agenda
2:00-2:10: Welcome & Introductions
2:10-2:40: Intro to vLLM: building, testing and contributing
2:40-3:10: Disaggregated P/D to Wide EP with llm-d
3:10-3:25: Networking Break
3:25-3:55: The Open-Sourcing of ERINE LLMs and Ecosystem Collaboration with vLLM
3:55-4:25: Performance Optimization Journey for Mooncake's LMCache Integration
4:25-4:55: How to implement vLLM on MACA
4:55-5:30: Closing Remarks, Q&A, and Social

​*Depending on the registration demand, we might change the meeting venue. Should that happen, we'll send out a notification.

In addition to Red Hat and MetaX, thank you to teams from BAIDU, Mooncake, InternLM, SHOPEN who are contributing to this meetup!