NVIDIA Vera Rubin NVL72 Delivers 30x Efficiency Gain for Agentic AI

NVIDIA Blog · rss · 2026-08-24

NVIDIA released data showing its Vera Rubin NVL72 system delivers up to 30x higher throughput per megawatt and 35x lower cost per million tokens than GB300 NVL72 on agentic workloads. Based on SemiAnalysis AgentX real-world trajectories, Vera Rubin utilizes extreme codesign techniques like disaggregated serving, rate matching, and distributed KV-caching to boost efficiency for long-context and tool-intensive tasks.

Original post →

More from Infra

Infra channel →