
MNN
by alibaba (organization)
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI. (description from the project’s GitHub page)
Repository facts
- Stars
- 16,238
- Forks
- 2,480
- Open issues and pull requests
- 50
- Primary language
- C++
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- alibaba · Organization
- Created
- Apr 15, 2019
- Last push
- Oct 16, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 1,946: uxlfoundation/oneDNN
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, a…
4,067 starsC++Apache-2.0Last push Oct 18, 2026
Rank 3,828: nndeploy/nndeploy
一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework
1,886 starsC++Apache-2.0Last push Aug 15, 2026
Rank 1,326: cactus-compute/cactus
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
6,128 starsC++Other licenseLast push Sep 26, 2026
Rank 1,076: Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB
💎1MB lightweight face detection model (1MB轻量级人脸检测模型)
7,548 starsPythonMITLast push Dec 29, 2023
Rank 3,063: ppogg/YOLOv5-Lite
🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~
2,489 starsC++GPL-3.0Last push Jun 22, 2024
Rank 5,629: sooftware/conformer
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
1,133 starsPythonApache-2.0Last push Jun 29, 2026