💬 MaxKB is a ready-to-use AI chatbot that integrates Retrieval-Augmented Generation (RAG) pipelines, supports robust workflows, and provides advanced MCP tool-use capabilities.

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …

Question and Answer based on Anything.

Manage GPU clusters for running AI models

A lightweight, powerful framework for multi-agent workflows

Distribution of `Loyalsoldier/v2ray-rules-dat`. Sync with the upstream every weeks.

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

FlashMLA: Efficient MLA decoding kernels

LLM inference in C/C++

Fully open reproduction of DeepSeek-R1

一种任务级GPU算力分时调度的高性能深度学习训练平台

NVIDIA Linux open GPU kernel module source

A generative speech model for daily dialogue.

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas…

Official code implementation of AAAI 2024 paper "StockMixer: A Simple yet Strong MLP-based Architecture for Stock Price Forecasting".

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Material for gpu-mode lectures

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…

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Jvedio 是本地视频管理软件，支持扫描本地视频并导入软件，建立视频库， 提取出视频的 唯一识别码，自动分类视频， 添加标签管理视频，使用人工智能识别演员，支持翻译信息， 基于 FFmpeg 截取视频图片，Window 桌面端流畅美观的应用软件

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Xiaomi Home Integration for Home Assistant

A generative world for general-purpose robotics & embodied AI learning.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

我的电视 电视直播软件，安装即可使用

Code for Machine Learning for Algorithmic Trading, 2nd edition.