SGLang Summit agenda: LinkedIn's 10K QPS ad ranking, SGLang on Vera Rubin
ying11231 · x · 2026-11-10
SGLang Summit 2026 runs November 12–13 at Fort Mason, San Francisco, with a two-day agenda spanning frontier infrastructure, silicon, models, and applications.
Highlights: Cloudflare on large-scale deployment; LinkedIn serving a small model for ads ranking at 10K+ QPS with sub-80ms scoring latency; Meta bringing PyTorch to SGLang; Alibaba extending HiCache for long-running agents; Perplexity's minimalist trainer for trillion-parameter models built with coding agents; Modal's early results using agents to develop and operate SGLang inference services; NVIDIA on bringing SGLang to Vera Rubin; Google on SGLang-TorchTPU for global production inference; SGLang Omni for interruptible conversations; Thinking Machines Lab and Meta on TorchTitan with Miles; Decagon on RL reducing hallucinations in customer-facing agents.
More from Companies & People
- Anthropic Staffs Up Claude Managed Agents to Run Thousands of Collaborating Agents Safely — threepointone · 2026-11-10
- Sakana AI signs France's Paris Call for AI safety alongside OpenAI and Anthropic — SakanaAILabs · 2026-11-10
- OpenAI staffer says academia unprepared as inference compute decides which fields accelerate — tw_killian · 2026-11-10
- Sierra's Bret Taylor bets on new grads: APX program marks two years — ZackRW · 2026-11-10
- AWS Quick, the AI workspace challenger: Free tier, $20/user Plus and six pricing tiers — shashib · 2026-11-10
- Johns Hopkins lab hiring postdocs in embodied intelligence, applications due Dec 11 — mangahomanga · 2026-11-10