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.

Original post →

More from Infra

Infra channel →