Stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
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
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
A high-throughput and memory-efficient inference and serving engine for LLMs
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
TensorFlow code and pre-trained models for BERT
The fundamental package for scientific computing with Python.
A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
PyTorch implementations of Generative Adversarial Networks.
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用
Python Implementation of Reinforcement Learning: An Introduction
An open-source tool-augmented conversational language model from Fudan University
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
A PyTorch implementation of the Transformer model in "Attention is All You Need".
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…
A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …
A Next-Generation Training Engine Built for Ultra-Large MoE Models
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI
Transformer: PyTorch Implementation of "Attention Is All You Need"
Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。
StarCraft II Client - protocol definitions used to communicate with StarCraft II.