The python library for real-time communication

这是一个用于显示当前网速、CPU及内存利用率的桌面悬浮窗软件，并支持任务栏显示，支持更换皮肤。

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

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

LLMs-from-scratch项目中文翻译

Master Python typing (type hints) with interactive online exercises!

Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

Fast and memory-efficient exact attention

pytorch 包教不包会

中文翻译的 Hands-On-Large-Language-Models (hands-on-llms)，动手学习大模型

LLM大模型（重点）以及搜广推等 AI 算法中手写的面试题，（非 LeetCode），比如 Self-Attention, AUC等，一般比 LeetCode 更考察一个人的综合能力，又更贴近业务和基础知识一点

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

Python package built to ease deep learning on graph, on top of existing DL frameworks.

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

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

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

Retrieval and Retrieval-augmented LLMs

MTEB: Massive Text Embedding Benchmark

ReLE中文大模型能力评测（持续更新）：目前已囊括291个大模型，覆盖chatgpt、gpt-5、o4-mini、谷歌gemini-2.5、Claude4、智谱GLM-Z1、文心一言、qwen-max、百川、讯飞星火、商汤senseChat、minimax等商用模型， 以及kimi-k2、ernie4.5、minimax-M1、DeepSeek-R1-0528、deepseek-v3.1、q…

Learning Large Language Model (LLM）(大语言模型学习)

Doing simple retrieval from LLM models at various context lengths to measure accuracy

📚 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

An extremely fast Python package and project manager, written in Rust.

Code and documentation to train Stanford's Alpaca models, and generate the data.

Notes about LLaMA 2 model