Stars
Implementation of my RAG system that won all categories in Enterprise RAG Challenge 2
A powerful tool for creating fine-tuning datasets for LLM
An extremely fast Python package and project manager, written in Rust.
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.
An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730
The official Python SDK for Model Context Protocol servers and clients
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
Python Client and Toolkit for DataFrames, Big Data, Machine Learning and ETL in Elasticsearch
SGLang is a fast serving framework for large language models and vision language models.
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.
Awesome Reasoning LLM Tutorial/Survey/Guide
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
Fully open reproduction of DeepSeek-R1
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agent RL)
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Modeling, training, eval, and inference code for OLMo