NVIDIA Blog· Vishal Ganeriwala·· 16 d ago
From Megawatts to Tokens: How NVIDIA Maximizes AI Factory Production
From Megawatts to Tokens: How NVIDIA Maximizes AI Factory Production
AI summary
NVIDIA introduced DSX at AI Infra Summit to improve AI-factory token throughput within a fixed power budget. Lambda validated DSX MaxLPS on a five-rack, 19-node HGX B200 cluster, running 19 nodes within the same budget as 16 at full power. Cluster token throughput rose 24%, from around four million to five million tokens per second, with performance per watt up 23%.
Selection record
Threshold 60Official, first-handFirst 62Second 62
AdmittedSum of both 124 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：NVIDIA AI工厂GPU算力与电网调度技术
- Why it was chosen
- Quantified results for DSX components in real deployments show practical ways to increase token throughput within fixed power budgets.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: NVIDIA Blog · blogs.nvidia.com