A Lean tactic for Canonical, a search procedure for terms in dependent type theory.

Wiki.js | A modern and powerful wiki app built on Node.js

A Non-Euclidean Rendering Engine for 3D scenes.

一个INI节点化编辑器。

A high-throughput and memory-efficient inference and serving engine for LLMs

🌈A rich set of enterprise-class UI components based on Ant Design and Blazor.

An orchestration platform for the development, production, and observation of data assets.

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

Reproduce R1 Zero on Logic Puzzle

💖🧸 アイリ, ultimate Neuro-sama like LLM powered Live2D/VRM living character life pod, near by you.

verl: Volcano Engine Reinforcement Learning for LLMs

A simple, easy-to-hack GraphRAG implementation

这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

Command and Conquer: Generals - Zero Hour

Command and Conquer: Modding Support

Command and Conquer: Red Alert

Graphs for Everyone

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

A modular graph-based Retrieval-Augmented Generation (RAG) system

Powerful automatic differentiation in C++ and Python

Open-source headless CMS built with ASP.NET Core (C#) and React, featuring REST APIs, GraphQL, and a GrapesJS page designer.

Use Stable Diffusion with C#

Example project demonstrating how to implement GraphRAG

DeepEP: an efficient expert-parallel communication library

Fast and memory-efficient exact attention

FlashMLA: Efficient MLA decoding kernels

Label Studio is a multi-type data labeling and annotation tool with standardized output format

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

A simple screen parsing tool towards pure vision based GUI agent