NVIDIA's Jetson AGX Orin accelerates AI and robotics applications and product creation.

NVIDIA announced on the 4th that it had released the Jetson AGX Orin 32GB production module.

The Jetson AGX Orin developer kit can perform up to 275 trillion operations per second and supports multiple concurrent AI application pipelines with NVIDIA Ampere architecture GPUs, next-generation deep learning and vision accelerators, high-speed I/O, and fast memory bandwidth.

Nvidia said the four Jetson Orin-based production modules announced at GTC will provide customers with a full range of server-class AI performance.

The production system is supported by the NVIDIA Jetson software stack, enabling developers to accelerate the building and deployment of AI solutions. Large, complex AI models can be used to develop solutions that address problems such as natural language understanding, 3D perception, and multi-sensor fusion.

In addition to the JetPack SDK with the NVIDIA CUDA-X acceleration stack, Jetson Orin supports several NVIDIA platforms and frameworks, including Isaac for robotics, DeepStream for computer vision, Riva for natural language understanding, the TAO toolkit to accelerate model development with pre-trained models, Metropolis, an application framework, and a set of developer tools and partner ecosystem that combines visual data and AI to improve operational efficiency and safety across industries.

The Jetson AGX Orin 32GB module is available now, with a 64GB version following in November. Two Orin NX production modules are expected later this year.