NVIDIA Vera Rubin NVL72 Delivers Leading Performance in MLPerf Inference v6.1 Debut
NVIDIA's first MLPerf Inference v6.1 preview submission of Vera Rubin NVL72 reports up to 3.7x higher throughput than GB300 NVL72 on Qwen3-VL and up to 2.5x on DeepSeek-R1, while GB300 NVL72 reached 99% scaling efficiency across 288 GPUs in four racks and software optimizations delivered up to 1.6x over v6.0.