

SGLang and NVIDIA DGX Spark Featured at InfiniEdge AI Workshop
Join the LF Edge InfiniEdge AI community during Open Source AI Week 2025 for a fast-paced session on building Generative AI on distributed edge clouds. We’ll share hands-on lessons from open collaboration across LF Edge, LF AI & Data, and the broader OSS ecosystem—covering edge inference, data pipelines, privacy-enhancing techniques, and AI agents running close to users and devices.
Who Should Attend
AI/ML engineers, edge/cloud practitioners
OSS contributors & maintainers
Product leaders exploring real-world edge GenAI
What You’ll Learn
How to run GenAI workloads on geo-distributed edge clouds
Design patterns for privacy, latency, and reliability
Practical demos with InfiniEdge AI and related OSS
Agenda
Welcome & OS AI Week context (5m)
InfiniEdge AI updates & roadmap, Tina Tsou, TSC Chair, InfiniEdge AI (LF Edge) (10m)
Deploy SGLang on NVIDIA DGX Spark, Pen C Li, NVIDIA, Jerry Zhou, SGLang (10m)
Scaling AI infra and Edge considerations, Ashok Prakash, Oracle (20m)
Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking, https://arxiv.org/abs/2509.21519, Yuandong Tian, ex-Research Scientist Director, Meta (15m)
Rick Cao, value proposition of GenAI in advertising & marketing, Head of Ads GenAI, Snap (10m)
Hands on experience of SGLang on Nvidia GPUs, Xinyuan Tong, SGLang will lead this session for participants (40m)
Q&A and contributor pathways (15–20m)
Branding & Attribution This event participates in Open Source AI Week 2025. All logos remain the property of their respective owners. Participation does not imply endorsement or sponsorship by other participants.
Warm up
Get familiar with InfiniEdge AI, join the code lab in September: https://luma.com/gqhu086t
Remote Participation
https://zoom.us/j/93878974263
Contact Questions? [email protected]