Catalogs >
AAEON >
hailo-8_m.2_starter_kit

hailo-8_m.2_starter_kit
2Pages

Catalog excerpts

Hailo-8™ M.2 starter kit The Hailo M.2 starter kit for AI applications delivers data center-class performance to edge devices with out-of-the-box passive thermal solutions for most system form factors Hailo-8™ M.2 Module An AI accelerator module based on the 26 teraoperations per second (TOPS) Hailo-8™ processor. Compatible with the NGFF M.2 form factor, the M.2 module can be plugged into an existing edge device with an M.2 socket to execute deep learning inferencing in real-time, utilizing low power for a broad range of market segments. KEY Features and Benefits Powered by 26 TOPS Hailo-8™ AI Processor with best-inclass power efficiency Enabling real-time, low latency and high-efficiency AI inferencing on edge devices Fast time to market using standard form factor module Leveraging Hailo’s comprehensive Dataflow Compiler and its support for standard AI frameworks, customers can easily and quickly port their neural network model Neural Network Application or Models Form Factor: NGFF M.2 B+M Key or A+E Key Dimensions: • +M key: 22 x 42 mm with B breakable extensions to 22 x 60 mm and 22 x 80 mm • +E key: 22 x 30 mm A Interface: PCIe Gen-3.0, 2-lanes Supported host architecture: x86 or Arm based (e.g. x86_64, aarch64) Supported OS: Linux (e.g. Ubuntu, Yocto) Supported AI frameworks: TensorFlow, ONNX and PyTorch Smart City Smart Home Smart Retail Ordering Information Contact us for ordering Hailo-8™ M.2 starter kit o

Open the catalog to page 1

Technical Highlights Featuring the Hailo-8™ AI Processor The Hailo-8™ AI processor, featuring up to 26 teraoperations per second (TOPS), significantly outperforms all other edge processors. Its area and power efficiency are far superior to other leading solutions by a considerable order of magnitude – at a size smaller than a penny even including the required memory. With an architecture that takes advantage of the core properties of neural networks, edge devices can now run deep learning applications at full scale more efficiently, effectively, and sustainably than traditional solutions,...

Open the catalog to page 2