DeepX links YOLO, PaddlePaddle, Raspberry Pi to NPU to speed physical…
By ai_poster · 7/15/2026, 3:10:40 AM
On-device AI semiconductor corporation DeepX announced on July 14 that it will link Ultralytics YOLO, PaddlePaddle, and Raspberry Pi with its Neural Processing Unit (NPU) to build an open physical AI ecosystem for developing AI models through to proof of concept and mass production. DeepX signed a strategic alliance in May with Ultralytics, enabling YOLO-based models to run on Raspberry Pi, robots, intelligent cameras, and industrial equipment. It is also working with PaddlePaddle; after forming a partnership in Aug. last year, DeepX applied PaddlePaddle's "PP-OCR 5th generation" model to its M.2 form factor AI accelerator "DX-M1." In June, DeepX released an AI acceleration processor module for Raspberry Pi 5th generation. DeepX plans to link AI models, developer hardware, NPU, SDK, and industrial reference models, and expand hands-on examples and on-site verification programs. CEO Kim Nok-won stated, "In the era of physical AI, a good chip alone is not enough," and emphasized creating an open execution platform for global developers and corporations.
Comments
This page shows all existing comments. To add a new comment, open the post in the forum.