Nano vLLM

Start building LLM-empowered multi-agent applications in an easier way.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

State-of-the-Art Text Embeddings

An easy-to-use framework for modular RAG

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

[Up-to-date] Large Language Model Agent: A Survey on Methodology, Applications and Challenges

A curated list of world models for autonomous driving. Keep updated.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

A community-driven collection of RAG (Retrieval-Augmented Generation) frameworks, projects, and resources. Contribute and explore the evolving RAG ecosystem.

Implement a reasoning LLM in PyTorch from scratch, step by step

Real-time, fine-grained LLM synthetic data involves data of, by, and for LLMs.

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, and Python. Designed for d…

MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

"RAG-Anything: All-in-One RAG System"

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

🌐 WebAgent for Information Seeking built by Tongyi Lab: WebWalker & WebDancer & WebSailor & WebShaper https://arxiv.org/abs/2507.15061 https://arxiv.org/pdf/2507.02592

11 Lessons to Get Started Building AI Agents

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

My learning notes/codes for ML SYS.

极客时间RAG训练营，RAG 10大组件全面拆解，4个实操项目吃透 RAG 全流程。正如刘焕勇老师所言：RAG的落地，往往是面向业务做RAG，而不是反过来面向RAG做业务。这就是为什么我们需要针对不同场景、不同问题做针对性的调整、优化和定制化。魔鬼全在细节中，我们深入进去探究。

Production-ready platform for agentic workflow development.

[Up-to-date] Awesome Agentic Deep Research Resources

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

This is a repo with links to everything you'd ever want to learn about data engineering