GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Unsupervised text tokenizer for Neural Network-based text generation.

Repository for OpenCV's extra modules

The QuantLib C++ library

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

C++ implementation of the Python Numpy library

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Configure Caffe in one hour for Windows users.

船长关于机器学习、计算机视觉和工程技术的总结和分享

Source code for paper: Learning to Track at 100 FPS with Deep Regression Networks, Held, et al. ECCV 2016

BanditPAM C++ implementation and Python package

Running BERT without Padding

My course design for compiler theory (Visualization).

An efficient framework for convolutional neural networks

Simple program to learn CNN (LeNet-5) in pure C

C++ implementation of Fast-and-Accurate-Unconstrained-Face-Detector

📚 数据结构

数据结构、计组、计网、操作系统、设计模式等计算机课程笔记