NVIDIA DSX squeezes 24% more token throughput from the same power budget, Lambda validates
NVIDIA Blog · rss · 2026-09-16
NVIDIA detailed its DSX AI factory platform at AI Infra Summit. Key results: Lambda ran 19 nodes within a 16-node power budget on HGX B200 servers, boosting cluster token throughput 24% (4M→5M tokens/s) and perf-per-watt 23%. NVIDIA's Eos factory, running Emerald AI's Conductor, has responded to 200+ demand-response signals from Silicon Valley Power, automatically cutting power from 4MW to 3MW while protecting priority jobs. DSX spans MaxLPS (dynamic power allocation), Flex (grid-responsive load balancing), OS, Sim, and reference designs with 800VDC. NVIDIA projects up to 40% more GPU capacity for Vera Rubin NVL72 factories within the same megawatt budget.
More from Infra
- To dethrone Postgres, new databases must prioritize ecosystem integrations from day one — mgill25 · 2026-11-02
- ESP32-powered 4-inch touchscreen builds a TUI dashboard for monitoring a DGX inference cluster — CATLLM · 2026-11-02
- OpenRouter crosses 10 quadrillion annualized token run rate, doubling every 10.5 weeks — deedydas · 2026-11-02
- Palmer Luckey asks: can you use datacenter RAM for things prohibited by the operator's terms of service? — avaitopiper · 2026-11-02
- Disable MTP for 20-30% faster local LLM inference on limited RAM — InternalMode8159 · 2026-11-02
- Kioxia up 216% in a year but down 68% from its June 2026 peak — zephyr_z9 · 2026-11-02