Supermicro releases reference architectures for Nvidia Vera Rubin accelerators enabling standardized scaling from 5MW to 1GW AI datacenters.
Super Micro Computer, Inc. announced on June 1, 2026, from San Jose, California and Taipei, the introduction of Data Center Building Block Solutions (DCBBS) Blueprints based on the NVIDIA Vera Rubin NVL72 and the NVIDIA HGX Rubin NVL8 platforms. Designed for gigawatt-scale AI data center deployment, these Blueprints start from building blocks of a single 1,152-GPU scalable unit that can be multiplied to virtually any size. The DCBBS Blueprints include design and delivery of an end-to-end total solution with a dedicated team of experts covering the full deployment lifecycle, providing compute, storage, networking, advanced liquid cooling, power distribution, and site infrastructure to accelerate time-to-online for large-scale liquid-cooled AI Factories.
Charles Liang, president and CEO of Supermicro, stated that "the NVIDIA Vera Rubin NVL72 platform sets a new standard for AI factory performance, and our DCBBS Blueprints give customers a proven, end-to-end path to build at any scale — from 5MW to 1GW." The NVIDIA Vera Rubin platform vastly improves AI Factory performance density, doubling speeds across multiple computing domains. Supermicro has a proven track record for deploying the world's largest liquid-cooled AI factories, featuring over 100,000 GPUs, with this experience built into every Blueprint to enable customers to move from design to fully operational faster than ever before.
DCBBS Blueprints address the practical implementation of advanced AI infrastructure by starting from a fixed constraint: available power. Blueprints for the NVIDIA Vera Rubin NVL72 feature a balanced bill-of-materials for a given power envelope, ranging from 5MW to 1GW, providing the right ratio of cooling capacity, power delivery, compute nodes, management nodes, high-performance storage nodes, context memory storage platform nodes, and networking to ensure optimal performance and prevent bottlenecks such as network oversubscription, power capacity limitations, thermal throttling, or other encumbrances.
Supermicro's implementation process begins with on-site facility surveys conducted by dedicated teams to analyze physical sites against deployment requirements, assessing loading dock access, data hall measurements and clearances, floor plans, and floor load ratings. Project design and proposals include customized buildout plans with the appropriate combination of DCBBS components, including cooling solutions such as in-row CDUs up to 1.8MW for fully direct liquid-cooled compatible facilities, liquid-to-air sidecars for facilities without facility water infrastructure, in-rack CDU options based on 52U rack configurations currently in development, and rear-door heat exchanger options for environments with higher ambient temperatures. The complete proposal includes a transparent bill of materials and a clear deployment timeline tailored to each customer's requirements and facility constraints.