OAID/Tengine

Tengine is a lite, high performance, modular inference engine for embedded device

51
/ 100
Established

This project helps embedded device manufacturers and AI solution providers efficiently deploy deep learning models onto resource-constrained hardware like AIoT devices. It takes trained neural network models and optimizes them to run quickly and with low memory usage on various chipsets (CPUs, GPUs, NPUs), enabling advanced AI features directly on the device. Developers building AI products for specialized hardware will find this useful.

4,510 stars. No commits in the last 6 months.

Use this if you need to deploy sophisticated AI models onto embedded systems and low-power devices, ensuring fast inference and minimal resource consumption.

Not ideal if you are developing AI models for cloud-based servers or powerful desktop environments with abundant computational resources.

embedded AI edge computing IoT deep learning deployment AIoT
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

4,510

Forks

979

Language

C++

License

Apache-2.0

Last pushed

Mar 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OAID/Tengine"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.