Supermicro Unveils Enterprise AI Solution Portfolio

Supermicro, Inc. expands its portfolio of solutions designed for NVIDIA Blackwell Architecture to the European market. The introduction of more than 30 solutions means Supermicro provides a comprehensive solution stack for NVIDIA HGX B200, GB200 NVL72, and RTX PRO 6000 Blackwell Server Edition deployments.

Through collaboration with NVIDIA, Supermicro's solution stack enables the deployment of NVIDIA Enterprise AI Factory validated design and supports the introduction of NVIDIA Blackwell Ultra solutions later this year, including NVIDIA GB300 NVL72 and HGX B300.

"Our collaboration with NVIDIA, combined with our global manufacturing capabilities and advanced liquid cooling technologies, enables European organizations to deploy AI factories with significantly improved efficiency and reduced implementation timelines," says Charles Liang, president and CEO of Supermicro.

In addition to Supermicro's selections of air-cooled and liquid-cooled NVIDIA HGX B200 systems and NVIDIA GB200 NVL72, Supermicro is expanding the portfolio, such as the new 4U front I/O liquid-cooled Supermicro NVIDIA HGX B200 system incorporating Supermicro's DLC-2 technology. The DLC-2 is designed to improve cooling efficiency and front I/O design simplifies cable and liquid-cooling hose management and serviceability, whereas the DLC-2 in-rack coolant distribution units (CDUs) are capable of removing 250kW of heat per rack. 

"NVIDIA Blackwell-powered AI factories accelerate demanding AI workloads and drive operational excellence across every function of the enterprise," says Chris Marriott, vice president, Enterprise Platforms at NVIDIA. "With its comprehensive portfolio and breakthrough energy efficiency, Supermicro's Blackwell systems transform data centers into AI factories that drive productivity and deliver maximum performance with minimal cost and power."

Supermicro is currently accepting orders for systems featuring NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, available across multiple form factors to enable AI deployment from data centers to network edge environments. The lineup includes a new 4U NVIDIA RTX PRO Server equipped with eight NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs and NVIDIA MGX PCIe Switch Board with ConnectX-8 SuperNIC, which combine PCIe Gen6 switching and 800 Gb/s networking capabilities in a single device to create an enterprise AI factory platform. Supermicro's NVIDIA-Certified Systems will integrate with NVIDIA Spectrum-X Ethernet networking, NVIDIA-Certified Storage, and NVIDIA AI Enterprise software through Supermicro's Data Center Building Block Solutions (DCBBS).

Supermicro's Data Center Building Block Solutions stack readiness for upcoming NVIDIA GB300 NVL72 and NVIDIA HGX B300 systems ensures technology transitions without infrastructure overhaul. The standardized solution architecture includes flexible floor plans, rack elevations, and a comprehensive bill of materials that can accommodate next-generation hardware while maintaining compatibility with existing networking, power, cooling, and management infrastructure. The NVIDIA AI Enterprise Factory validated design provides additional assurance with rigorous testing and optimization for NVIDIA Blackwell accelerated computing. Featuring NVIDIA networking and the full stack NVIDIA AI Enterprise software platform, these designs allow customers to scale their reasoning model deployments.

Supermicro's approach includes data center design consultation, solution validation, and professional onsite deployment services. The integration with SuperCloud Composer software provides data center-level management and infrastructure orchestration capabilities. With global manufacturing facilities across San Jose, Europe, and Asia, Supermicro delivers manufacturing capacity for liquid-cooled rack systems.

For more information, please visit https://www.supermicro.com/en/accelerators/nvidia

Sources: Press materials received from the company and additional information gleaned from the company’s website.