DEEPX expands NPU integrations across YOLO, PaddlePaddle and Raspberry Pi
DEEPX expanded its NPU integrations across Ultralytics YOLO, Baidu PaddlePaddle and Raspberry Pi to connect physical-AI development, proof-of-concept work and industrial deployment.
Evidence notes
- The Ultralytics integration lets developers export YOLO models into DEEPX format and run them through the company’s edge-AI runtime.
- DEEPX and PaddlePaddle have enabled PP-OCR 5 workloads on the DX-M1 accelerator, extending the stack into industrial OCR and real-time inference.
- Raspberry Pi 5 provides a development and validation layer before applications move into robots, industrial cameras, edge gateways and smart-factory equipment.
Company context
DEEPX develops ultra-low-power AI semiconductor chips for on-device inference across robotics and autonomous systems. Its processors are designed to enable real-time perception and decision-making directly on robots without reliance on cloud infrastructure.