hailort/README.md

HailoRT

HailoRT is a lightweight, production-grade runtime library that runs on the host processor and provides a robust user-space library (the HailoRT Library) with intuitive APIs in C/C++ for optimized performance

HailoRT consists of the following main components:

• HailoRT Library.
• HailoRT CLI - a command line application used to control the Hailo device, run inferences, collect statistics and device events, etc.
• HailoRT PCIe Driver - the device driver used to manage the Hailo device, communicate with the device, and transfer data to/from the device; it includes the Hailo-8 firmware that runs on the Hailo device and manages its boot and control.
• pyHailoRT - HailoRT Python API, which wraps the runtime library.
• HailoRT GStreamer element (HailoNet).

HailoRT supports Linux and Windows, and it can be compiled from sources to be integrated with various x86 and ARM processors.

Usage

See hailo.ai developer zone documentation (registration is required for full documentation access).

For compilation instructions, see Compiling HailoRT from Sources.

For HailoRT API examples - see HailoRT examples.

Changelog

See hailo.ai developer zone - HailoRT changelog (registration required).

Licenses

HailoRT uses 2 licenses:

• libhailort, pyhailort & hailortcli - distributed under the MIT license
• hailonet (GStreamer plugin) - distributed under the LGPL 2.1 license

Contact

Contact information and support is available at hailo.ai.

About Hailo-8™

Hailo-8 is a deep learning processor for edge devices. The Hailo-8 provides groundbreaking efficiency for neural network deployment. The Hailo-8 edge AI processor, featuring up to 26 Tera-Operations-Per-Second (TOPS), significantly outperforms all other edge processors. Hailo-8 is available in various form-factors, including the Hailo-8 M.2 Module.

The Hailo-8 AI processor is designed to fit into a multitude of smart machines and devices, for a wide variety of sectors including Automotive, Smart Cities, Industry 4.0, Retail and Smart Homes.

For more information, please visit hailo.ai.