NVIDIA Vera Rubin NVL72 Delivers Leading Performance in MLPerf Inference v6.1 Debut
NVIDIA's Vera Rubin NVL72 debuts in MLPerf Inference v6.1 with up to 3.7x higher throughput than GB300 NVL72 and 99% scaling efficiency at 288 GPUs.
In its first MLPerf Inference preview submission, NVIDIA's Vera Rubin NVL72 achieved up to 3.7x higher throughput than GB300 NVL72 on Qwen3-VL and 2.5x on DeepSeek-R1. A 288-GPU GB300 NVL72 submission across four racks reached 99% scaling efficiency on the DeepSeek-R1 offline benchmark. Software optimizations delivered up to 1.6x gains over v6.0, leveraging TensorRT-LLM, vLLM, Dynamo, disaggregated serving, and NVFP4 precision.
- Vera Rubin NVL72: up to 3.7x throughput vs GB300 NVL72 on Qwen3-VL; 2.5x on DeepSeek-R1
- 288-GPU GB300 NVL72 submission achieved 99% scaling efficiency on DeepSeek-R1 offline
- Software optimizations yielded up to 1.6x performance gains over v6.0 submissions
- Nebius also submitted Vera Rubin NVL72 preview results
- Vendors
- NVIDIA
- Products
- Vera Rubin NVL72GB300 NVL72
- AI models
- DeepSeek-R1Qwen3-VL
From the original article
4 min read at blogs.nvidia.com
System performance, efficient infrastructure scaling and continuous software optimization are key levers that determine AI inference economics. Higher system performance means more tokens generated, resulting in higher revenue. Efficient scaling means throughput grows proportionally as hardware gets added, requiring fewer resources to serve users at scale.
By Zhihan Jiang · blogs.nvidia.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.