Skip to main content

NVIDIA-Certified Supermicro Systems bring together Supermicro’s broad portfolio of workload optimized systems, NVIDIA GPUs and NVIDIA networking validated for performance, manageability, security, and scalability. Supermicro spans the complete range of NVIDIA-Certified Systems: Datacenter, Workstation and Edge. The certification tests exercise the performance and functionality on a set of software that represents a wide range of real-world applications.

A lineup of Supermicro NVIDIA Certified Systems

Categories of NVIDIA-Certified Systems

Large Scale AI Training and HPC OptimizedCertified for large-scale deep learning and HPC with highest-performance GPUs, high-speed GPU-to-GPU interconnect with NVIDIA NVLink®, PCIe 5.0 switches, fastest flash storage and networking supporting NVIDIA GPUDirect RDMA and Storage.
AI Training & Inferencing, General Purpose, Virtualization OptimizedRackmount, multi-node, and blade servers that support GPUs for wide range of accelerated workloads, AI-enabled applications, visualization, 3D simulation, virtual workstation.
Enterprise Edge and Industrial Edge OptimizedCertified edge systems running accelerated applications outside a traditional data centers. These systems are designed to be deployed in controlled or restrictive environments, such as retail store, factory or telco micro data center.
WorkstationPowerful desktop workstations designed and certified for enterprise and professionals to accelerate AI and data science model development, 3D rendering, and creative visual design.

Key Benefits

PerformanceNVIDIA-Certified Systems are configured to deliver excellent performance for a diverse range of workloads. Customers can run most accelerated applications on these systems – including GPU-optimized software from the NVIDIA NGC™ catalog and commercially available applications.
ManageabilityCertification tests are run on the NVIDIA Cloud Native Stack using Kubernetes for orchestration. This validates that certified servers can be fully managed by leading IT management frameworks.
SecurityNVIDIA-Certified Systems secure workflows by protecting data at the platform, network, and application layers. Whether these systems are deployed in a datacenter or at the edge, customers can be assured that they don’t have to compromise on security when running accelerated applications.
ScalabilityNVIDIA-Certified servers are tested to validate both multi-GPU and multi-node performance, as well as the performance of multiple workloads running on a single GPU with Multi-Instance GPU (MIG) technology.

NVIDIA-Certified Systems Software Support

With the continued rollout of advanced applications and workloads, customers require manageable, secure, and scalable servers for their data centers. Supermicro's compelling lineup of high-performance servers supporting NVIDIA GPUs and DPUs includes a growing number of NVIDIA-Certified Systems, with many more currently undergoing the certification process. Each server/GPU configuration earns its own certification.

Full-Stack Support
  • TensorFlow
  • Deep Stream
  • Py Torch
  • RAPIDS
  • NVIDIA TensorRT
  • NVIDIA Clara
  • NVIDIA Triton
  • NVIDIA AI Software
NVIDIA Virtual GPU Software
CUDA, GPU and Networking Drivers, GPU and Network Operator
Host OS and Drivers
Supermicro’s NVIDIA-Certified Systems