NVIDIA Announces AI Foundry Service and NIM Inference Microservices to Power Generative AI

New Offerings Enhance NVIDIA's AI Platform for Real-Time, Low-Latency Applications

SANTA CLARA, Calif.--(BUSINESS WIRE)--NVIDIA (NASDAQ: NVDA) today announced NVIDIA AI Foundry, a new service that provides developers with access to the latest NVIDIA AI software, tools, and infrastructure, and NVIDIA NIM (Network Inference Microservices), a set of inference microservices that enable developers to deploy AI models quickly and efficiently.

NVIDIA AI Foundry provides a comprehensive platform for AI development, including access to NVIDIA's latest AI software, such as the NVIDIA AI platform, the NVIDIA CUDA platform, and the NVIDIA TensorRT platform. Developers can also access NVIDIA's AI tools, such as the NVIDIA NGC catalog and the NVIDIA Metropolis platform, as well as NVIDIA's AI infrastructure, such as the NVIDIA DGX systems and the NVIDIA Jetson platform.

NVIDIA NIM is a set of inference microservices that enable developers to deploy AI models quickly and efficiently. NIM microservices are designed to be lightweight and scalable, and they can be deployed on a variety of platforms, including servers, clouds, and edge devices. NIM microservices can be used to accelerate a wide range of AI applications, such as image recognition, natural language processing, and speech recognition.

"NVIDIA AI Foundry and NVIDIA NIM are powerful new offerings that will empower developers to create and deploy the next generation of AI applications," said Jensen Huang, founder and CEO of NVIDIA. "With these new offerings, NVIDIA is providing developers with the tools and infrastructure they need to build the future of AI."

For more information on NVIDIA AI Foundry, please visit the NVIDIA website. For more information on NVIDIA NIM, please visit the NVIDIA website.