LMSYS Online meetup on efficient LLM deployment and serving (Oct 16)
We are excited to invite you to join the online meetup co-hosted by SGLang, FlashInfer, and MLC LLM! The three closely collaborating projects will share their different perspectives on efficient LLM deployment and serving. We also intend for this to be an opportunity for people from the community to interact with one another.

Tentative Agenda:
4:00 - 4:45 pm PST: SGLang overview, updates, Q&A
        Speakers: Liangsheng Yin, Lianmin Zheng, Ke Bao
        Featured  topics: Low CPU overhead scheduling in SGLang,
                                       Deepseek MLA optimizations, Fast JSON decoding
4:50 - 5:35 pm PST: FlashInfer overview, updates, Q&A
        Speakers: Zihao Ye
        Featured topics: Kernel generation for high performance LLM serving
5:40 - 6:25 pm PST: MLC LLM overview, updates, Q&A
        Speakers: Ruihang Lai, Yixin Dong, Tianqi Chen
        Featured topics: Universal LLM deployment, Low-latency serving,
                                      Fast grammar-based decoding

Submit this form to receive the invite link.
Sign in to Google to save your progress. Learn more
Email *
Your Name *
Your Affiliations(s)
What do you most expect from the meetup?
Do you want to be invited to future events?
Submit
Clear form
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google. - Terms of Service - Privacy Policy

Does this form look suspicious? Report

Google Forms