OAID/Tengine
A lightweight, high-performance inference engine for deploying deep learning models on embedded and edge devices.
Not currently ranked — collecting fresh signals.
star history
Tengine is developed by OPEN AI LAB to enable fast and efficient deployment of deep learning neural network models on embedded devices. It uses C language for core modules and implements a fully separated front-end and back-end design to support rapid porting across heterogeneous computing units including CPU, GPU, and NPU. The framework includes modules for operator registration, model parsing, computation graph scheduling, and hardware backend execution.
Frequently asked
- What is OAID/Tengine?
- A lightweight, high-performance inference engine for deploying deep learning models on embedded and edge devices.
- Is Tengine open source?
- Yes — OAID/Tengine is open source, released under the Apache-2.0 license.
- What language is Tengine written in?
- OAID/Tengine is primarily written in C++.
- How popular is Tengine?
- OAID/Tengine has 4.5k stars on GitHub.
- Where can I find Tengine?
- OAID/Tengine is on GitHub at https://github.com/OAID/Tengine.