verl: Volcano Engine Reinforcement Learning for LLMs

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

The official Python SDK for Model Context Protocol servers and clients

Memory for AI Agents; Announcing OpenMemory MCP - local and secure memory management.

Profile-Based Long-Term Memory for AI Applications

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

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

🦜🔗 Build context-aware reasoning applications

Community-maintained LangChain integrations

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

SGLang is a fast serving framework for large language models and vision language models.

Train transformer language models with reinforcement learning.

Fully open reproduction of DeepSeek-R1

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

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

Python bindings for llama.cpp

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

OpenCompass is an LLM evaluation platform, supporting a wide range of models (InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Unify Efficient Fine-Tuning of 100+ LLMs

Unsupervised text tokenizer for Neural Network-based text generation.

⚡ A Fast, Extensible Progress Bar for Python and CLI