NVIDIA Vera Rubin NVL72 在 MLPerf Training v6.1 中性能最高達 Blackwell Ultra 的 2 倍
NVIDIA Vera Rubin NVL72 Achieves up to 2x Blackwell Ultra Performance in MLPerf Training v6.1
NVIDIA Vera Rubin NVL72 在 MLPerf Training v6.1 的性能最高達 Blackwell Ultra 的 2 倍。Vera Rubin 架構在該版評測中首次亮相,NVIDIA 在七項基準測試中全數勝出。NVIDIA 表示,早期結果顯示其 CUDA 軟件堆疊已相當成熟。
As AI agents tackle increasingly complex workflows, reducing time-to-train is critical for rapidly iterating on both models and the agents they power. MLPerf...
As AI agents tackle increasingly complex workflows, reducing time-to-train is critical for rapidly iterating on both models and the agents they power. MLPerf Training v6.1 marks the debut of the NVIDIA Vera Rubin architecture, and these early results demonstrate that its CUDA software stack is already highly mature. NVIDIA swept all seven benchmarks, with the Vera Rubin NVL72 platform delivering…
來源:NVIDIA Technical Blog:Agentic AI / Generative AI · developer.nvidia.com