Inspur Introduces Three AI Servers, First to Support NVIDIA A30 and A10 GPUs

In addition, Inspur A100 GPU server helps Northwestern Medicine improve 10x in AI model training speed and 100x in data prep

SAN JOSE, Calif., Apr. 12, 2021 – At NVIDIA GTC 2021, Inspur Information, a leading IT infrastructure solutions provider, introduced three new GPU servers (NF5468M6, NF5468A5 and NF5280M6), which fully support the latest NVIDIA A30, A10 and A100 Tensor Core GPUs to meet the demand for AI computing power in multiple computing scenarios. The Inspur AI server is the first in the industry to fully support NVIDIA® Ampere architecture GPUs and has obtained NVIDIA-certified servers for EGX platform, delivering a complete and competitive next-generation AI computing platform.

“Inspur is committed to delivering users leading AI solutions and innovations by continuously adapting to evolving AI computing scenarios,” said Liu Jun, VP and GM, AI and HPC, Inspur Information. “Through our agile product design and development capabilities, Inspur is the first to launch and mass-produce AI servers supporting NVIDIA A30 and A10 chips, providing more diverse product options to meet the needs of different industries, scales and scenarios.”

“The NVIDIA A30 Tensor Core GPUs offer more possibilities for mainstream AI inference and enterprise workloads, while the NVIDIA A10 Tensor Core GPUs are suitable for AI computing scenarios in media such as images and video,” said XX of NVIDIA. “Powered by the A30 GPU and A10 GPU, each Inspur AI server product can efficiently scale with application requirements and flexibly match user needs in multiple dimensions.”

Delivering AI Solutions for Industry

Currently, an Inspur server powered with A100 GPUs is in use at Northwestern University Feinberg School of Medicine, where the institute is pilot testing high-performance data pipelines to enable deep learning experiments without having to deal with separate, costly copies of legacy health system enterprise data. With the state-of-the-art performance of Inspur’s A100-based training platform, the pilot program has provided significant performance improvements not just in model training but in overall project delivery. With a 10x improvement in training speed, and 100x improvement in data prep, Northwestern Medicine can rapidly prototype, iterate, and ultimately deploy deep learning models directly into the healthcare environment.

“With our high-speed data pipes and the Inspur A100 GPU server, we can quickly iterate and use the state-of-the-art in AI to help our patients,” said Dr. Mozziyar Etemadi, anesthesiologist and Chief Data Engineer of the Northwestern Institute for Augmented Intelligence in Medicine (I-AIM).

Furthermore, Inspur servers supporting NVIDIA® Ampere architecture are also widely used in deep learning, image recognition, natural language understanding, intelligent recommendation and other intelligent scenarios in various industries, helping enterprise users accelerate AI innovation.

Inspur’s All-New GPU Servers Supporting A30, A10 and A100

NF5468M6: ultra-flexible for AI workloads, supports 2x Intel 3rd generation Xeon processor and 8x NVDIA A100/A40/A30 GPUs, 16x NVIDIA A10 GPUs, or 20x NVIDIA T4 GPUs; supports up to 12x 3.5-inch hard drives for large local storage in 4U chassis; flexibly adapts to latest AI accelerators and smartNICs and has the unique function of switching topologies with one click for various AI applications including AI cloud, IVA(Intelligent Video ), video processing, etc.

NF5468A5: versatile AI server featuring 2x AMD Rome/Milan CPUs and 8x NVIDIA A100/A40/A30 GPUs; N+N redundancy design enables 8x 350W AI accelerators in full-speed operations for superior reliability; the CPU-to-GPU non-blocking design allows interconnection without the PCIe switch communication, achieving faster commutation efficiency.

NF5280M6: purpose-built for all scenarios, with 2x Intel 3rd generation Xeon processor and 4x NVIDIA A100/A40/A30/A10 GPUs or 8x T4 NVIDIA GPUs in 2U chassis, capable of long-term stable operation at 45°C. The NF5280M6 is equipped with the latest PFR/SGX technology and trusted security module design, which is suitable for demanding AI applications.

Inspur is the world’s leading AI server vendor with a rich array of AI computing products and works closely with AI customers to help achieve high order-of-magnitude performance improvements for AI applications in speech, semantics, image, video, search, and more.