Supermicro is now shipping NVIDIA Vera Rubin NVL72 racks integrated with its Data Center Building Block Solutions (DCBBS) and its DLC-2 direct liquid cooling stack. The racks follow the VR NVL72 design NVIDIA launched at CES 2026: 72 NVIDIA Rubin GPUs and 36 NVIDIA Vera CPUs in a single liquid-cooled rack that operates as one machine, spread across 18 1U compute trays with four Rubin GPUs and two Vera CPUs each. Nine sixth-generation NVIDIA NVLink switch trays connect the compute trays and deliver 216 TB/s of scale-up bandwidth, and each rack carries 20.7 TB of HBM4 and up to 54 TB of LPDDR5X.
“We have spent years building the liquid-cooling stack, the manufacturing capacity, and the deployment teams for exactly this moment,” said Charles Liang, president and CEO of Supermicro. “Our customers can now order a Scalable Unit and receive production-ready systems with end-to-end integration, because we design and build every layer between the cold plate and the cooling tower.”
DLC-2 From Cold Plate to Cooling Tower
NVIDIA designed the Vera Rubin platform around direct liquid cooling, and Supermicro says the resulting heat load has to move through the full fluid distribution loop, from the cold plates through manifolds to the cooling tower. Supermicro builds that path from its own portfolio, which covers cold plates, manifolds, hose kits, rack power shelves, in-row CDUs, in-rack CDUs, Liquid-to-Air sidecar CDUs, rear door heat exchangers, and facility-side cooling towers. Supermicro first outlined its liquid cooling plans for Vera Rubin NVL72 nel mese di gennaio.
The shipping NVL72 package pairs the racks with Supermicro in-row cooling distribution units (CDUs) rated at 1.8MW each and deployed with N+1 redundancy, plus optional rear door heat exchangers to capture residual heat. Supermicro tests and validates every rack with the full liquid cooling stack, which it says speeds time-to-online once the racks are deployed.
Scalable Unit Blueprint and Cluster Deployment
Supermicro’s DCBBS Blueprint defines a balanced bill of materials for a given power envelope, from 5 MW to gigawatt scale, the same approach the company took with its Vera Rubin NVL4 DCBBS Blueprint in June. One Vera Rubin NVL72 Scalable Unit spans 16 compute racks with 1,152 Rubin GPUs and 331 TB of HBM4, sized alongside matching cooling capacity, power delivery, high-performance storage, context memory storage, and networking.
Supermicro also handles networking integration and cabling to the NVIDIA Reference Architecture, covering the AI compute fabric, the converged fabric, and out-of-band management, and a Supermicro team runs each project from site survey and design through integration, testing, delivery, deployment, and ongoing support. Supermicro rack-scale compute is also part of Cisco’s Secure AI Factory, which added Vera Rubin NVL72 support in August.
Amazon