NVIDIA has announced that its AI inference platform, newly expanded with NVIDIA A30 and A10 GPUs for mainstream servers, has achieved record-setting performance across every category on the latest release of MLPerf.

MLPerf is the industry’s established benchmark for measuring AI performance across a range of workloads spanning computer vision, medical imaging, recommender systems, speech recognition and natural language processing, a release said.

Debuting on MLPerf, NVIDIA A30 and A10 GPUs combine high performance with low power consumption to provide enterprises with mainstream options for a broad range of AI inference, training, graphics and traditional enterprise compute workloads.

Cisco, Dell Technologies, Hewlett Packard Enterprise, Inspur and Lenovo are expected to integrate the GPUs into their highest volume servers starting this summer.

NVIDIA achieved these results taking advantage of the full breadth of the NVIDIA AI platform —  encompassing a wide range of GPUs and AI software, including TensorRT and NVIDIA Triton Inference Server — which is deployed by leading enterprises, such as Microsoft, Pinterest, Postmates, T-Mobile, USPS and WeChat, the company added in a release.

“As AI continues to transform every industry, MLPerf is becoming an even more important tool for companies to make informed decisions on their IT infrastructure investments,” said NVIDIA general manager and vice president of Accelerated Computing Ian Buck.

“Now, with every major OEM submitting MLPerf results, NVIDIA and our partners are focusing not only on delivering world-leading performance for AI, but on democratizing AI with a coming wave of enterprise servers powered by our new A30 and A10 GPUs,” he added.

NVIDIA’s Expanding AI Platform

The NVIDIA A30 and A10 GPUs are the latest additions to the NVIDIA AI platform, which includes NVIDIA Ampere architecture GPUs, NVIDIA Jetson AGX Xavier and Jetson Xavier NX, and a full stack of NVIDIA software optimized for accelerating AI.

The A30 delivers versatile performance for industry-standard servers, supporting a broad range of AI inference and mainstream enterprise compute workloads, such as recommender systems, conversational AI and computer vision.

The NVIDIA A10 GPU accelerates deep learning inference, interactive rendering, computer-aided design and cloud gaming, enabling enterprises to support mixed AI and graphics workloads on a common infrastructure.

The NVIDIA Jetson platform, based on the NVIDIA Xavier system-on-module, provides server-class AI performance at the edge, enabling a wide variety of applications in robotics, healthcare, retail and smart cities. Built on NVIDIA’s unified architecture and the CUDA-X software stack, Jetson is the platform capable of running all the edge workloads in compact designs while consuming less than 30W of power.

Availability

NVIDIA A100 GPUs are available in servers from leading manufacturers and in the cloud from all major cloud service providers. Additionally, A100 GPUs are featured across the NVIDIA DGX systems portfolio, including the NVIDIA DGX Station A100, NVIDIA DGX A100 and NVIDIA DGX SuperPOD.

The A30 and A10, which consume just 165W and 150W, are expected in a wide range of servers starting this summer, including NVIDIA-Certified Systems that go through rigorous testing to ensure high performance across a wide range of workloads.

The Jetson AGX Xavier and Jetson Xavier NX system-on-module are available from distributors globally.

NVIDIA Triton and NVIDIA TensorRT are both available on NGC, NVIDIA’s software catalog.