alibaba / MNNLinks
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/README.md). MNN TaoAvatar Android - Local 3D Avatar Intelligence: apps/Android/Mnn3dAvatar/README.md
☆13,828Updated this week
Alternatives and similar repositories for MNN
Users that are interested in MNN are comparing it to the libraries listed below
Sorting:
- TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is …☆4,605Updated 7 months ago
- ncnn is a high-performance neural network inference framework optimized for the mobile platform☆22,533Updated this week
- MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.☆5,029Updated last year
- PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）☆7,210Updated 7 months ago
- 🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉☆4,335Updated 3 weeks ago
- Open Machine Learning Compiler Framework☆12,984Updated this week
- An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.☆2,910Updated 2 years ago
- Simplify your onnx model☆4,255Updated 4 months ago
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆12,526Updated 3 weeks ago
- Open standard for machine learning interoperability☆20,079Updated this week
- 💎1MB lightweight face detection model (1MB轻量级人脸检测模型)☆7,485Updated 2 years ago
- ONNX-TensorRT: TensorRT backend for ONNX☆3,175Updated last month
- MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架☆4,807Updated last year
- ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator☆18,841Updated this week
- Bolt is a deep learning library with high performance and heterogeneous flexibility.☆955Updated 8 months ago
- FeatherCNN is a high performance inference engine for convolutional neural networks.☆1,224Updated 6 years ago
- MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.☆4,655Updated last year
- OpenVINO™ is an open source toolkit for optimizing and deploying AI inference☆9,434Updated this week
- NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone…☆6,138Updated last year
- oneAPI Deep Neural Network Library (oneDNN)☆3,949Updated this week
- A high performance and generic framework for distributed DNN training☆3,715Updated 2 years ago
- Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX☆2,504Updated 3 months ago
- MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Co…☆5,818Updated 4 months ago
- The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologi…☆3,095Updated last week
- LightSeq: A High Performance Library for Sequence Processing and Generation☆3,300Updated 2 years ago
- Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators☆1,548Updated 6 years ago
- A primitive library for neural network☆1,369Updated last year
- YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documenta…☆10,252Updated 6 months ago
- Pre-trained Deep Learning models and demos (high quality and extremely fast)☆4,340Updated 3 weeks ago
- Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.☆3,221Updated 5 months ago