NVIDIA Vera Rubin NVL72 Posts First MLPerf Inference Preview Results

NVIDIA announced its Vera Rubin NVL72 system's first MLPerf Inference v6.1 preview results, showing up to 3.7x higher throughput than its GB300 NVL72 system on the Qwen3-VL benchmark. The system also achieved 2.5x higher throughput on DeepSeek-R1, demonstrating significant performance improvements through hardware-software codesign.