NVIDIA joins new SGLang Consortium after 5 GPU generations of collaboration
NVIDIAAI · x · 2026-11-14
NVIDIA officially joined the newly formed SGLang Consortium. The collaboration spans five generations of accelerated computing from Ampere to Vera Rubin, with 2+ years of joint engineering, 60+ day-zero model launches, and 10+ developer events and meetups. NVIDIA says it will keep working with the SGLang and Miles communities to advance open-source AI.
Related event: LMSYS Launches SGLang Consortium with NVIDIA, AMD, Google, Meta and More(6 posts)→
More from Infra
- China Took 59% of 600,000+ Industrial Robots Installed in 2025; Humanoid Shipments Still Tiny — ingliguori · 2026-11-14
- SGLang joins NVIDIA AI Enterprise with NIM-certified inference microservices — ying11231 · 2026-11-14
- LMSYS and NVIDIA: Vera CPUs cut agentic RL episode time by 11% in Miles tests — ying11231 · 2026-11-14
- Databricks AI agents take 2nd in Meta kernel challenge with 2.5X speedup over SGLang — Yuchenj_UW · 2026-11-14
- 1.2 billion GPUs in circulation — 'one for every seven people; how do we arm the other six?' — shakoistsLog · 2026-11-14
- Morgan Stanley: Google TPUs to hit 35% of global AI chip demand, nearly matching NVIDIA's 36% — cgarciae88 · 2026-11-14