NVIDIA
GPU-accelerated SDK for building real-time video analytics pipelines on Jetson and x86 GPUs.
DeepStream builds streaming vision AI pipelines that decode, batch, infer and track across many camera streams on NVIDIA hardware, and is documented under NVIDIA's Metropolis vision AI framework. Release 9.1 adds access to thirteen agentic skills for video understanding.
Jetson device, edge server or cloud GPU instance
Specifications taken from current manufacturer documentation and last checked on 2026-09-08.
Source: manufacturer documentation
Specifications are summarised from publicly published manufacturer material and are provided for orientation only. Always confirm current figures directly with the manufacturer before purchasing or designing in.
Open-source vision model family covering detection, segmentation, classification, pose and oriented boxes.
Open-source inference package and server that turns a computer or edge device into a vision deployment target.