Repo đang lênCập nhật hằng ngày từ GitHub

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

A curated list of foundation models for vision and language tasks

Kubediff: a tool for Kubernetes to show differences between running state and version controlled configuration.

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

Official PyTorch implementation of "VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization" (CVPR 2021)

All-in-one terminal covering 30+ protocols — SSH, RDP, SFTP, databases, Kubernetes and more. With a built-in AI Agent that runs multi-turn shell commands autonomously.

NekroAgent 是一个面向多人互动场景的跨平台 Agent 框架，集 Claude Code 沙盒执行、工作区编排、长期记忆、结构化 MCP 管理与可视化控制台于一体，兼具高扩展性、多模态交互、实时状态推送和自动化运行能力。项目支持 QQ、Discord、Telegram、Minecraft、BilibiliLive、WeChat、Email、SSE(SDK) 等多种平台接入，应用于构建高智能聊天机器人，可扩展为具备代码执行、工具调用、插件协作和复杂任务处理能力的通用 Agent 系统

基金,大盘,股票,虚拟货币状态栏显示小应用

Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.

A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.

LibCity: An Open Library for Urban Spatial-temporal Data Mining

Unifying 3D Mesh Generation with Language Models

A lightweight knowledge base for people and agents, with ultra fast indexing and most precise retrieval.

PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations

企业微信/微信 安全使用的 LLM 个人助手/客服, 也支持 dify 工作流

《机器学习宝典》包含：谷歌机器学习速成课程（招式）+机器学习术语表（口诀）+机器学习规则（心得）+机器学习中的常识性问题 （内功）。该资源适用于机器学习、深度学习研究人员和爱好者参考！

꼼꼼한 딥러닝 논문 리뷰와 코드 실습

Training library for local feature detection and matching

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

An autonomous research colleague — from a question to a compiled manuscript, while you sleep.

Research on Tabular Deep Learning: Papers & Packages

A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

Cool vision, learning, and graphics papers on Cats!

[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.

Samples for Intel® oneAPI Toolkits

SIMPLE YET COMPLICATED 🚩

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

:books: A collection of Deep Learning based Image Colorization and Video Colorization papers.

JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.

React design system for agentic interfaces. Every free BoardUI component as source, with a working AI chat app on your own model key as the homepage.

Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.

这是我自己做的一个类似滴滴打车的Android出行项目，主要针对滴滴等出行平台一直饱受质疑的“人车不符”问题，以及当前越发火热的或计划和出海战略，给出行项目增加了下面几个功能： 1. RFID识别验证功能：在司机证件或者车内识别硬件嵌入RFID识别芯片，乘客使用手机读取到芯片信息，并且通过网络发送到出行平台数据库进行验证（我用JNI加了一个C语言的MD5加密算法对识别到的信息进行了加密）。如果不是合规的“人”或“车”，则不能完成订单并向平台或监管单位汇报当前位置。（为了方便读者测试，可以使用手机读取任何一个加密或非加密RFID芯片，比如银行卡、公交卡等，我在代码中的验证前阶段把芯片信息都换成我自己的司机信息，确保读者测试时可以收到服务器的回复） 2. 海外版功能：点击切换当前语言。 3. 司机证件号码识别功能：读取司机证件上的证件号码，也可以用来与出行平台数据库的接单司机信息进行。I complete this whole project on my own . Including Android application programming，web server ( Apache + PHP + MySQL), and UI. 1．Map route planing。You can use mobile phone choose pick up & destination address，application provide address name hint and draw optimized route for user , then call car for you. 2．RFID authentication function：User can use application to scan driver license or other RFID hardware, then use NDK MD5 algorithm encrypt RFID number, and send it to Web Server Database, check with driver information and authenticate ID number , if ID number coherent with driver info , send back driver information to User and continue call car order . record user location and alert if ID not coherent. 3．Driver License Number Recognition : Application can recognize driver license digit number ,and also can send to web server for authentication & feed back result to user.

A self-learning tutorail for CUDA High Performance Programing.

TensorFlow 最佳学习资源大全（含课程、书籍、博客、公开课等内容）

The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows.

Pytorch Implementation For LPRNet, A High Performance And Lightweight License Plate Recognition Framework.

You want to build with AI, but setting up the right context, prompts, and workflows takes time. AI Factory handles all of that so you can focus on what matters — shipping quality code.

Get answers for CLI commands from ChatGPT right from your terminal

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

Open-source CLI for unrestricted AI - Access powerful models without censorship

Tools for handling multimodal data in machine learning projects.

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

LangChain powered shell command generator and runner CLI

Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime.

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11, YOLOv12 for ROS 2