LLM inference in C/C++

Vibe Coding 从入门到精通教程｜AI 结对编程工作流｜Prompt、Skill、Workflow、上下文管理、codex实战指南

提示工程的指南、论文、讲座和资源，提示词逆向工程

The code for the ebook Ray Tracing in One Weekend by Peter Shirley translated to CUDA by Roger Allen. This work is in the public domain.

High performance physically based renderer in C++11

Lightning fast & tiny C++/CUDA neural network framework

Tensor library for machine learning

Neural Network Libraries

Single Header C++ Implementation of NumPy NdArray.

Jsmn is a world fastest JSON parser/tokenizer. This is the official repo replacing the old one at Bitbucket

RakNet is a cross platform, open source, C++ networking engine for game programmers.

Minimal Example of Using Vulkan for Compute Operations. Only ~400LOC.

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Integration of Fastspeech Text to Mel generation and fast Vocoder Squeezewave

Lightweight, extremely high-performance JSON parser for C++11

High-efficiency floating-point neural network inference operators for mobile, server, and Web

Super fast C++ .PNG writer/reader

Stable Diffusion in pure C/C++

A fast and easy-to-use PLY parsing library in a single c++11 header and cpp file

OpenGL Image (GLI)

C++ implementation of Qwen-LM

simple C++ json library. (clone of kazuho/picojson)

A tiny, single-header <canvas>-like 2D rasterizer for C++

A small, easily embedded language implemented in a single .c file

A tiny immediate-mode UI library