

SGLang & AMD SF MEET-UP
You are invited for "SGLang and AMD Meet-up" on August 22nd, 2025, from 4:30 PM to 8:30 PM at Shack15 in San Francisco's Ferry Building! Join us for an engaging evening featuring hands-on workshop, tech talks, networking opportunities, delicious food and drinks. Seats are limited. We encourage you to register in advance to secure your spot
What to Expect
Agenda
•4:30 PM Workshop Registration
•4:45 PM Hands-on Workshop by AMD & SGLang team. See details below
•5:00 PM Meetup registration
•5:30 PM AMD Exec Talk
•5:35 PM SGLang Open-Source Talk: H2 2025 Roadmap, review past, present & upcoming enhancements & features by Yineng Zhang
•5:50 PM SGLang AMD Inference Talk: AMD Contribution and Advantages, past, present and future, key directions
•6:05 PM xAI talk on large scale expert parallelism (EP) in the open-source SGLang project, enabling trillion-parameter MoE models across GPU clusters & speed up time to inference by Cheng Wan
•6:20 PM AMD ROCm Tech Talk - AITER and MORI
•6:30 - 8:30 PM Happy Hour & Networking
Workshop details:
An instructor-led, hands-on GPU workshop equips you with tips, tricks and techniques on how to optimize performance with SGLang on AMD GPUs.