Inspur

Inspur logo

Integrate Cloud Computing and AI Total Solutions in Your Business

Named by Gartner as one of the top 3 server manufacturers in the world, Inspur is a leading data center and cloud computing solutions provider. Through engineering and innovation, Inspur aspires to deliver robust, performance-optimized, purpose-built solutions to address emerging technology arenas and challenges.

 
Product

4U 8x A100 GPU Server for AI Training and Inference

Versatile 8GPU Server for AI Workloads

Ranking first in single sever performance in MLPerf 0.7, it supports 8 fully interconnected NVLink 3.0 NVIDIA A100 Tensor Core GPUs, and 2 AMD® EPYC® Rome processors enabling PCIe4.0 in a 4U space, NF5488A5 delivers outstanding AI performance of 5 petaFLOPS and ultra-high data throughput, making it ideal choice for AI applications like image, video and voice processing, financial analysis and virtual assistants.

  1. Record-Setting AI Performance
  2. Extreme Hardware Design
  3. Accelerating AI Training

Best single sever performance in the MLPerf v0.7 benchmark, setting 18 performance records and achieving 549,000 inferences per second in the ResNet50 inference task.

8x fully interconnected NVLink 3.0 NVIDIA A100 GPUs, 2x AMD EPYC Rome processors enabling PCIe4.0 in 4U and delivering 5 petaFLOPS and high data throughput.

Supports the latest A100 80G GPU with HBM2e, doubling the memory capacity of its predecessor and a 30% increase in GPU memory bandwidth in a single node, delivering 15% performance increase in AI model training tasks with tens of billions of parameters.

 

NF5280M6

2U capacity, unlimited possibilities.

Powered with 2 latest 3rd Gen Intel Xeon Scalable processors, this highly versatile 2U server comes in workload-optimized configurations that deliver robust compute, storage and I/O capabilities: up to 360 TB storage capacity, NVMe accelerated performance, 11 flexible expansion slots, and support for 4 dual-width or 8 single-width GPUs.

  1. Robust Memory
  2. High Storage Capacity
  3. Accelerated Performance

• support for U.2 / M.2 / E1.S NVMe
• Intel Optane Persistent Memory 200 Series

• up to 360 TB (20x LFF)

• up to 24x SFF NVMe SSD
• up to 4x dual width or 8x single width GPUs

 

NF5688M6

NF5688M6 is a new generation of NVLink AI server developed by Inspur for ultra-large-scale data centers with high performance, high compatibility and strong expansion. It is the first to support 2 Intel latest Ice Lake CPUs and 8 NVIDIA latest NVSwitch fully interconnected in 6U space. 500W A100 GPU. NF5688M6 is the industry's first air-cooled product that supports 500W A100 GPU, and can provide up to 12 PCIe expansion products, and supports self-developed dual-wide N20X, NV DPU and other smart network cards. Combined with the leading AI computing resource sched -uleing platform AIStation, it fully releases the powerful AI computing performance of up to 5 pe-taFLOPS.

  1. Leading Technology
  2. Stable Quality
  3. Optimal Design
  4. Excellent Ecology
  • 2 Intel Ice Lake processors, using 10nm process
  • 8 NVIDIA A100 GPUs, 600GB/s bandwidth NVSwitch fully interconnected
  • Support multi-instance GPU (MIG), greatly improving GPU resource utilization
  • Up to 10 200G HDR InfiniBand, high-speed interconnection expansion
  • Support hard/soft RAID scheme to ensure data security
  • N+N redundant power supply to ensure reliable operation of the system
  • Optimized heat dissipation design to support stable work under high ambient temperature
  • Intelligent remote management to quickly locate faults
  • The industry's only air-cooled support 500W A100 GPU
  • High performance ratio, GPU: computing IB: storage IB=8:8:2
  • Modular design, flexible operation, easy operation and maintenance
  • Leading support for Inspur N20X, NV-DPU, A/T customer smart network card
  • Extensive and mature x86+CUDA global development ecology
  • Leading deep learning framework support, TensorFlow/PyTorch/flying paddle, etc.
  • Efficiently support large-scale CV/NLP/NMT/DLRM model training and inference
  • Easily connect with Yuannao ecosystem partners and provide rich industry AI solutions