Artificial intelligence (AI) chipmaker Hailo has launched its M.2 and Mini PCIe modules for a variety of edge devices.
The modules allow users to integrate AI capabilities for accelerating a range of deep learning-based applications in smart cities, smart retail, Industry 4.0, smart homes and more. For example, the modules could be used in AI edge boxes that allow cameras and sensors to be connected to a single intelligent processing device in outdoor deployments.
The Hailo modules — that deliver 26 tera operations per second (TOPS) and have a power efficiency of 3 TOPS — can be plugged into any existing edge device with an M.2 or Mini PCIe socket.
Hailo said its Hailo-8 M.2 module has been integrated into Foxconn’s Boxiedge, an AI processing solution for edge video analytics, with no redesign required for the PCB. The Boxiedge solution provides for standalone AI inference nodes for applications such as smart cities, smart retail, smart medical and Industry 4.0.
Hailo's AI acceleration modules seamlessly integrate into standard frameworks, such as TensorFlow and ONNX, which are both supported by Hailo's comprehensive Dataflow Compiler. Customers can quickly port their Neural Networks (NNs) into the Hailo-8 processor, ensuring high-performance, enabling smarter AI products, and accelerating time-to-market.