Supermicro now ships NVIDIA Vera Rubin NVL72 GPU racks for AI inference workloads.

Super Micro Computer, Inc. is now shipping NVIDIA Vera Rubin NVL72 racks integrated with Supermicro's Data Center Building Block Solutions (DCBBS) and its direct liquid cooling stack (DLC-2). Supermicro's DCBBS now supports all critical computing infrastructure to speed time-to-online for NVIDIA Vera Rubin NVL72 deployments.

"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, 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. Our development of DLC-2 technology is what sets Supermicro apart and allows us to deliver the most complete solution for the NVIDIA Vera Rubin platform."

The NVIDIA Vera Rubin platform was designed in conjunction with direct liquid cooling technology to deliver AI-throughput-per-watt at efficiency levels unachievable with air cooling alone. With far greater AI operations per second comes a proportionally greater heat load: heat must be moved through the full fluid distribution loop, from the cold plates through manifolds to the cooling tower. Supermicro tests and validates every rack with the full liquid cooling stack, speeding up time-to-online when deployed.

Supermicro's path-to-production spans from the mechanical engineering of individual system nodes to the large-scale manufacturing of liquid-cooled racks and full onsite deployment of clusters based on NVIDIA reference architecture. The company's DCBBS provides unmatched thermal expertise and a comprehensive in-house portfolio of liquid cooling components: cold plates, manifolds, hose kits, rack power shelves, in-row cooling distribution units (CDUs), in-rack CDUs, liquid-to-air sidecar CDUs, rear door heat exchangers, and facility-side cooling towers.

Supermicro's DCBBS Solutions for NVIDIA Vera Rubin NVL72 include:

• NVIDIA Vera Rubin NVL72 racks: 72 NVIDIA Rubin GPUs and 36 NVIDIA Vera CPUs in a single liquid-cooled rack operating as one machine. Eighteen 1U compute trays, each with four Rubin GPUs and two Vera CPUs, 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.

• Supermicro in-row cooling distribution units rated at 1.8 MW per CDU, deployed with N+1 redundancy

• Optional Supermicro Rear Door Heat Exchangers to ensure capture of residual heat load

• Networking integration and cabling services based on NVIDIA Reference Architecture, including the AI compute fabric, converged fabric, and out-of-band management cabling

To ease deployment, Supermicro's DCBBS Blueprint defines a balanced bill-of-materials for a given power envelope, from 5 MW to gigawatt scale. The blueprint based on one Vera Rubin NVL72 Scalable Unit provides 1,152 NVIDIA Rubin GPUs with 331 TB of HBM4 memory across 16 compute racks, with balanced cooling capacity, power delivery, high-performance storage, context memory storage, and networking. A Supermicro team manages the entire project across site survey, design, integration, testing, delivery, deployment, and ongoing support.