Vertiv's new 7MW reference architecture for the NVIDIA GB200 NVL72 transforms data centers into AI-capable infrastructures. Optimizing deployment speed and energy efficiency, this design features advanced power management and hybrid cooling solutions, ensuring reliable operation in demanding environments.
Vertiv (NYSE: VRT), a global provider of critical digital infrastructure, today announced the release of a complete 7MW reference architecture co-developed with NVIDIA for the NVIDIA GB200 NVL72 platform. This architecture will enable customers to transform traditional data center infrastructures into AI factories capable of supporting enterprise AI applications.
The reference architecture accelerates the deployment of the NVIDIA GB200 NVL72 liquid-cooled rack-scale platform, supporting loads of up to 132kW per rack. It adopts an end-to-end approach to infrastructure design, optimizing deployment speed, performance, resilience, cost, energy efficiency, and scalability for current and future data centers.
“We are proud to deepen our collaboration with NVIDIA to enable AI-driven data centers of today and tomorrow,” said Giordano (Gio) Albertazzi, CEO of Vertiv. “As a leader in critical power and cooling infrastructure, Vertiv is uniquely positioned to support the NVIDIA GB200 NVL72 platform. Our portfolio of high-performance power and cooling solutions, combined with our global scale, will enable customers to deploy AI data centers faster, more efficiently, and with greater flexibility to address densification, dynamic workloads, retrofits, and future-ready designs.”
Jensen Huang, founder and CEO of NVIDIA, stated, “New data centers are built for accelerated computing and generative AI, with architectures significantly more complex than those for general-purpose computing. With Vertiv's world-class cooling and power technologies, NVIDIA can realize our vision to reinvent computing and build a new industry of AI factories that produce digital intelligence to benefit every company and industry.”
Vertiv's power and cooling infrastructure is closely integrated with the NVIDIA Blackwell platform. The reference architecture simplifies and accelerates the deployment of AI workloads in both new and existing data centers while reducing risk and enabling standardization across sites. The complete critical power infrastructure is designed to significantly reduce stranded power by aligning AI clusters with data center capacity blocks. The hybrid liquid- and air-cooling infrastructure leverages the interdependent impacts of both approaches to efficiently manage high-density heat removal. Additionally, the design includes guidance for optional Open Compute Project-inspired systems, such as DC power shelves.
This reference architecture is part of the Vertiv™ 360AI portfolio of reference designs aimed at helping customers navigate integrated power and cooling solutions for AI and other high-performance computing applications. Key benefits of the co-developed reference architecture for the NVIDIA GB200 NVL72 design include:
As enterprises embrace AI at an unprecedented pace, Vertiv is reshaping the future of critical power and cooling to support accelerated computing, offering the most complete portfolio of critical digital infrastructure capable of managing the unique requirements of AI and other accelerated computing applications.
If you would like more information about this product, please feel free to contact us. Recommend other popular products for you: Liebert ITA2 Series UPS factory