Super Micro Computer, Inc. (NASDAQ: SMCI) announced it has begun shipping Nvidia Vera Rubin NVL72 racks integrated with its Data Center Building Block Solutions (DCBBS) and direct liquid cooling stack (DLC-2), according to a company press release dated Sept. 23, 2026.

Each Vera Rubin NVL72 rack contains 72 Nvidia Rubin GPUs and 36 Nvidia Vera CPUs arranged across 18 compute trays. The trays connect through nine sixth-generation Nvidia NVLink switch trays, delivering 216 TB/s of scale-up bandwidth. Each rack provides 20.7 TB of HBM4 memory and up to 54 TB of LPDDR5X memory.

Supermicro's DCBBS Blueprint defines a bill-of-materials for a single Vera Rubin NVL72 Scalable Unit that includes 16 compute racks housing 1,152 Nvidia Rubin GPUs and 331 TB of HBM4 memory. The blueprint covers power envelopes ranging from 5 MW to gigawatt scale.

The liquid cooling components included in the offering span cold plates, manifolds, hose kits, rack power shelves, in-row cooling distribution units rated at 1.8 MW each deployed with N+1 redundancy, in-rack CDUs, liquid-to-air sidecar CDUs, rear door heat exchangers, and facility-side cooling towers. Networking integration and cabling services based on Nvidia Reference Architecture are also included.

"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."

Supermicro states that each rack is tested and validated with the full liquid cooling stack prior to deployment. The company says a single team manages projects across site survey, design, integration, testing, delivery, deployment, and ongoing support.