LLM inference in C/C++

LeetCode Problems' Solutions

Event-driven network library for multi-threaded Linux server in C++11

Code repository of all OpenGL chapters from the book and its accompanying website https://learnopengl.com

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

高性能并行编程与优化 - 课件

Tutorial for the Vulkan graphics and compute API

一个基于C++11的轻量级网络框架，基于线程池技术可以实现大并发网络IO

C++20 实现的跨平台、header only，易用的高性能http库; modern c++(c++20), cross-platform, header-only, easy to use http framework

Simple, light-weight and easy-to-use asynchronous components

A collection of modern C++ libraries, include coro_http, coro_rpc, compile-time reflection, struct_pack, struct_json, struct_xml, struct_pb, easylog, async_simple etc.

Anton's OpenGL 4 Tutorials book - Demo Code

UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

Project HashClash - MD5 & SHA-1 cryptanalysis

torchcomms: a modern PyTorch communications API

小彭老师特意从零开始研发的一款教学用，基于 C++17 回调函数的异步 HTTP 服务器

A tiny deep learning training framework implemented from scratch in C++ that follows PyTorch's API.

使用 C++ 模板元编程模拟 Lisp

c++20 coroutine with epoll and queue

Tiny C++ LLM inference implementation from scratch