In2infinity/dragon-npu

🐉 Revolutionary NPU framework for Linux | 24,988 FPS face recognition | AMD XDNA support | World's first complete NPU stack

32
/ 100
Emerging

This tool helps anyone using AI models on Linux to significantly speed up tasks like face recognition, object detection, or language model responses. It takes your existing AI models, like those for computer vision or natural language processing, and optimizes them to run incredibly fast and efficiently on dedicated NPU hardware found in many modern laptops. This is for AI developers, researchers, or power users who want to deploy high-performance AI applications directly on their Linux machines.

No commits in the last 6 months.

Use this if you need to run AI models on Linux at extreme speeds and efficiency, leveraging the dedicated Neural Processing Units (NPUs) in your hardware.

Not ideal if you primarily work on Windows or macOS, or if you don't have NPU hardware and are content with CPU-based AI inference.

AI deployment edge computing computer vision natural language processing AI acceleration
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 8 / 25

How are scores calculated?

Stars

36

Forks

3

Language

Python

License

MIT

Last pushed

Aug 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/In2infinity/dragon-npu"

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