《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验

已上架 Chrome / Edge 商店 🚀 把 B 站视频变成学习资源的浏览器扩展：字幕阅读、双语对照、AI 章节概览、划词解释和带时间戳的笔记

DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers

A lightweight library for xPU kernel JIT compilation

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.

Learn CUDA with PyTorch

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.

A Tiny biped duck robot 🦆

A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.

making the official triton tutorials actually comprehensible

📚 Solutions for C++ Primer 5th exercises.

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

🤱🏻 Turn any webpage into a desktop app with one command.

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Learn it. Build it. Ship it for others.

Warp is an agentic development environment, born out of the terminal.

Github mirror of trition-lang/triton repo.

⛷ Lightweight Markdown app to help you write great sentences.

The Art of Debugging Open Book

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

A Claude Code skill that turns any codebase into a beautiful, interactive single-page HTML course for non-technical vibe coders.

Solve puzzles. Improve your pytorch.

TokenSpeed is a speed-of-light LLM inference engine.

The Hybrid Task Graph Scheduler API

A one-page-only CGraph-API-liked DAG project.

🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.

🎙️ A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!