Thursday, November 12, 2026
1:30 PM – 3:30 PM PST
SGLang Summit Workshop by LMSYS: Local AI Coding Lab
About this event
A two-hour hands-on workshop at SGLang Summit where attendees serve a Qwen model locally with SGLang on a cloud RTX PRO 6000 Blackwell GPU and connect a coding agent to it. Approval required, sold out with a waitlist.
Run by LMSYS Org with the SGLang and NVIDIA Local AI teams at Fort Mason. Participants get a short overview of NVIDIA hardware for running models locally, deploy a Qwen model with SGLang, test the endpoint with inference requests, connect a coding agent to it and use the agent on a coding task, possibly debugging mini-sglang.
Bring a laptop. Python, command-line and basic Docker familiarity is recommended. Each attendee connects to a cloud-hosted GPU instance.
Registration is free but needs host approval and an SGLang Summit pass (Full or Expo). It was sold out with an active waitlist when checked, so confirm availability on Luma. 1:30 to 3:30 PM Pacific.
Organized by
Community events for SGLang, an open-source high-performance inference framework for large language models maintained by LMSYS Org.