Ultralytics partners with DEEPX to bring YOLO inference to edge NPUs
Ultralytics announced a DEEPX partnership and a supported export integration for deploying YOLO models on low-power NPU hardware.

Evidence notes
- Ultralytics announced a DEEPX partnership for deploying YOLO models on DEEPX NPU hardware.
- The integration adds a supported format=deepx export path so teams can compile and run YOLO models on DEEPX edge devices.
- The companies position the combined stack for physical-AI uses including robotics, industrial automation, autonomous systems, and other real-time vision workloads.
Company overview
Ultralytics develops YOLO computer-vision models and a platform for preparing data, training models and deploying inference. Robotics teams use the stack for detection, segmentation, pose estimation and tracking in autonomous navigation, manipulation, inspection and drone workflows.