Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

🐱 跨平台互动桌宠 BongoCat，为桌面增添乐趣！

Training Large Language Model to Reason in a Continuous Latent Space

PyTorch-native post-training at scale

🤖一个基于 WeChaty 结合 ChatGPT / Claude / Kimi / DeepSeek / Ollama等Ai服务实现的微信机器人 ，可以用来帮助你自动回复微信消息，或者社群分析/好友管理，检测僵尸粉等...

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Inference at the speed of light.

depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.

SkyRL: A Modular Full-stack RL Library for LLMs

An intuitive and low-overhead instrumentation tool for Python

神级Cursor Rule

对知乎网页端排版进行优化

SGLang is a high-performance serving framework for large language models and multimodal models.

Nano vLLM

Material for gpu-mode lectures

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

DSPy: The framework for programming—not prompting—language models

A collection of useful .gitignore templates

vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

My learning notes for ML SYS.

Efficient Triton Kernels for LLM Training

Reasoning LLMs optimized for Chisel code generation

Agentic RAG R1 Framework via Reinforcement Learning

A flush-reload side channel attack implementation