Together AI Berlin meetup: n8n and NVIDIA engineers on running open models in production
togethercompute · x · 2026-10-21
Together AI's Open Haus in Berlin brought together engineers from n8n and NVIDIA to share what it takes to run open models in production. Slides covered routing for cache-hit optimality: global routing picks the right DC by model, capacity and session tenancy, promptcachekey keeps a conversation sticky, and prefix-hash routing directs requests to the longest cached prefix to boost prefix-cache hit rates.
More from Companies & People
- AI film goes from idea to IMAX premiere and greenlit series in 14 days — lmoroney · 2026-10-21
- Musk lays out SpaceX roadmap: 20GW compute next year, $500B–$1T ARR by end of 2027 — elonmusk · 2026-10-21
- Kimi K3 pretraining researcher Nathan Chen joins Jeff Dean's startup Discovery Loop — ivan_bezdomny · 2026-10-21
- Andrew Ng: NYU Center for Data Science is recruiting a Department Chair — andrewgwils · 2026-10-21
- Shenzhen robotics founder meets Scobleizer: hardware-software fusion as the US-China bridge — Scobleizer · 2026-10-21
- Anthropic's cloud partnerships turn messy as rivals-turned-providers starve it of compute — TechCrunch AI · 2026-10-21