A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

"DeepTutor: AI-Powered Personalized Learning Assistant"

slime is an LLM post-training framework for RL Scaling.

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

LM engine is a library for pretraining/finetuning LLMs

Public repository for Agent Skills

AWS-native chatbot using Bedrock

🚀🚀 「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!

Train transformer language models with reinforcement learning.

Example apps for the Apps SDK

Stremio - Freedom to Stream

On-device TTS model by Neuphonic

Efficient and easy multi-instance LLM serving

Tongyi Deep Research, the Leading Open-source Deep Research Agent

The Official Player2 Godot Plugin

Hypermodern Python Cookiecutter

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Godot Engine official documentation

PyTorch tutorials.

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

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

Kimi K2 is the large language model series developed by Moonshot AI team

GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.

A language for constraint-guided and efficient LLM programming.

Nano vLLM

Ongoing research training transformer models at scale

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

“连续八年成为全世界最受喜爱的语言，无 GC 也无需手动内存管理、极高的性能和安全性、过程/OO/函数式编程、优秀的包管理、JS 未来基石" — 工作之余的第二语言来试试 Rust 吧。本书拥有全面且深入的讲解、生动贴切的示例、德芙般丝滑的内容，这可能是目前最用心的 Rust 中文学习教程 / Book

Tensor library for machine learning