Supermicro Announces Support for Upcoming NVIDIA Vera Rubin NVL72, HGX Rubin NVL8 and Expanded Rack-Scale Manufacturing Capacity for Liquid-Cooled AI Solutions

Data Center Building Block Solutions® (DCBBS) and Advanced Direct Liquid Cooling (DLC) Technology with Supermicro US Based In-House Design/Manufacturing Accelerate Time to Deployment of Next Generation Liquid-cooled AI Infrastructure

Supermicro, Inc. (NASDAQ: SMCI), a total IT solution provider for AI, cloud, storage, and 5G/edge, today announced expansions in manufacturing capacity and liquid-cooling capabilities, in collaboration with NVIDIA, to enable first-to-market delivery of data center-scale solutions optimized for the NVIDIA Vera Rubin and Rubin platforms.

Leveraging accelerated development and collaboration with NVIDIA, Supermicro is uniquely positioned to rapidly deploy the flagship NVIDIA Vera Rubin NVL72 and NVIDIA HGX™ Rubin NVL8 systems. Supermicro’s proven Data Center Building Block Solutions® (DCBBS) approach delivers streamlined production, extensive customization options, and faster time-to-deployment, giving customers a decisive competitive edge in next-generation AI infrastructure.

Flagship Products:

• NVIDIA Vera Rubin NVL72 SuperCluster: the premier rack-scale system unifies 72 NVIDIA Rubin GPUs and 36 NVIDIA Vera CPUs, NVIDIA ConnectX^®-9 SuperNICs, and NVIDIA BlueField^®-4 DPUs into a coherent platform with NVIDIA NVLink 6 and scales-out with NVIDIA Quantum-X800 InfiniBand and NVIDIA Spectrum-X Ethernet to power the AI industrial revolution. It delivers 3.6 exaflops NVFP4 performance, 1.4 PB/s HBM4 bandwidth, and 75 TB of fast memory. Built on the 3rd-generation NVIDIA MGX rack architecture for superior serviceability, reliability, and availability, Supermicro’s implementation incorporates an enhanced data center-scale liquid-cooling technology stack with in-row Coolant Distribution Units (CDUs). This enables scalable warm-water cooling operation that minimizes energy consumption and water usage while maximizing density and efficiency.
• 2U Liquid-cooled NVIDIA HGX Rubin NVL8 Systems: this compact 8-GPU system is optimized for AI and HPC workloads, delivering breakthrough performance and efficiency to enterprises for intelligence at scale. It provides 400 petaflops NVFP4, 176 TB/s HBM4 bandwidth, 28.8 TB/s NVLink bandwidth, and 1600 Gb/s NVIDIA ConnectX-9 networking SuperNICs. Supermicro delivers rack-scale design with maximum deployment flexibility and configuration options supporting flagship x86 CPUs such as next-generation Intel® Xeon® or AMD EPYC™ processors. Available options include a high-density 2U busbar design for optimal rack integration featuring Supermicro’s industry-leading advanced Direct Liquid Cooling (DLC) technology.

Key NVIDIA Vera Rubin Platform Features Include:

• NVIDIA NVLink™ 6: High-speed interconnects enabling unprecedented GPU-to-GPU and CPU-to-GPU communication for the training and inference of massive mixture-of-experts models.
• NVIDIA Vera CPU: NVIDIA-designed custom Arm cores delivering 2x performance over the previous generation, with spatial multithreading (88 cores/176 threads), 1.2 TB/s LPDDR5X memory bandwidth with 3x more capacity and 1.8 TB/s NVLink-C2C bandwidth to GPUs (2x previous).
• 3rd Generation Transformer Engine: Optimized acceleration for processing long-context workloads, narrow-precision computations critical to scale modern AI workloads.
• 3rd Generation Confidential Computing: Delivers rack-scale confidential computing with a unified, GPU-level trusted execution environment that keeps models, data, and prompts protected and isolated.
• 2nd Generation RAS Engine: Advanced reliability, availability, and serviceability features, including real-time health checks without downtime.

Additionally, the NVIDIA Vera Rubin platform benefits from newly announced NVIDIA Spectrum-X Ethernet Photonics networking, built on the Spectrum-6 Ethernet ASIC (102.4 Tb/s switching on TSMC 3nm with 200G SerDes co-packaged optics and fully shared buffers). This delivers 5x power efficiency, 10x reliability, and 5x application uptime compared to traditional pluggable optics. Available models include the liquid-cooled SN6800 (409.6 Tb/s CPO, 512x 800G ports), SN6810 (102.4 Tb/s CPO, 128x 800G ports), and SN6600 (pluggable, 128x 800G ports, air/liquid-cooled). Complementing this is Supermicro-based storage solutions using the Petascale all-flash storage server and JBOF system supporting the NVIDIA BlueField -4 DPU running a variety of data management solutions.

Supermicro’s strategic investments in expanded manufacturing facilities and a comprehensive end-to-end liquid-cooling technology stack are purpose-built to streamline production and deployment of fully liquid-cooled NVIDIA Vera Rubin and Rubin platforms. Combined with the modular DCBBS architecture, these capabilities accelerate deployment and time-to-online by enabling rapid configuration, rigorous validation, and seamless scaling of high-density platforms—ensuring customers achieve first-to-market advantages.

More information about Data Center Building Block Solutions® (DCBBS) from SuperMicro

More information about Advanced Direct Liquid Cooling (DLC) Technology from Supermicro