SGLang Summit 2026 agenda: LinkedIn serves ads model at 10K QPS, NVIDIA brings SGLang to Vera Rubin
DavidBennett__ · x · 2026-11-05
SGLang Summit 2026 takes place November 12–13 at Fort Mason Center, San Francisco, expecting 2,000+ engineers and researchers, sponsored by ai&. Announced track highlights:
- AI in Production: Cloudflare on large-scale deployment; LinkedIn serving an ads-ranking small model at 10K+ QPS with scoring latency under 80 ms
- SGLang & Miles: Meta bringing PyTorch to SGLang; Alibaba extending HiCache for long-running agents
- Agentic Engineering: Perplexity's minimalist trainer for trillion-parameter models built with coding agents; Modal using agents to develop and manage SGLang inference services
- Training & Post-Training: Thinking Machines Lab and Meta on TorchTitan with Miles; Decagon using RL to improve instruction following and cut hallucinations in customer-facing agents
- Hardware: NVIDIA on porting SGLang to Vera Rubin; Google on SGLang-TorchTPU for global production inference
- Real-Time & Media: SGLang Omni for interruptible conversations; HeyGen on GPU optimization to cut serving costs; MiniMax on film-production AI workflows
More from coding & agent
- Vector search finds resemblance, not proof: where Microsoft Fabric Graph fits — WirelessLife · 2026-11-05
- 20 AI agent memory tools to know in 2026, from Mem0 to Graphiti — MaryamMiradi · 2026-11-05
- Databricks recipe: multi-tenant Genie isolation via OAuth custom identity claims + ABAC — Wise_Ear_4064 · 2026-11-05
- How do you teach AI agents company-specific jargon? Four glossary approaches, none great — ladybawss · 2026-11-05
- Garry Tan spends $200K/yr on a 23-skill Claude Code setup — benchmarks show elaborate harnesses can lose to vanilla — echen · 2026-11-05
- Teams experiment: cheap models for subagents, top model only on the primary agent — cramforce · 2026-11-05