The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

Open Source Computer Vision Library

The POCO C++ Libraries are powerful cross-platform C++ libraries for building network- and internet-based applications that run on desktop, server, mobile, IoT, and embedded systems.

AHN: Artificial Hippocampus Networks for Efficient Long-Context Modeling

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Awesome Reasoning LLM Tutorial/Survey/Guide

Multilingual Document Layout Parsing in a Single Vision-Language Model

Text-audio foundation model from Boson AI

Tensor library for machine learning

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

Tensor library for machine learning

SGLang is a high-performance serving framework for large language models and multimodal models.

Fast, Flexible and Portable Structured Generation

✨✨[CVPR 2025] Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

A curated list of Rust code and resources.

aria2 is a lightweight multi-protocol & multi-source, cross platform download utility operated in command-line. It supports HTTP/HTTPS, FTP, SFTP, BitTorrent and Metalink.

Simple, secure & standards compliant web server for the most demanding of applications

A C++ header-only HTTP/HTTPS server and client library

An open-source project for Windows developers to learn how to add AI with local models and APIs to Windows apps.

Shared to msvcrt.dll or ucrtbase.dll and optimize the C/C++ application file size.

Open standard for machine learning interoperability

Low-bit LLM inference on CPU/NPU with lookup table

FlashInfer: Kernel Library for LLM Serving

Macro-header for compile-time C obfuscation (tcc, win x86/x64)

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…

AI app store powered by 24/7 desktop history. open source | 100% local | dev friendly | 24/7 screen, mic recording

A throughput-oriented high-performance serving framework for LLMs

The Python programming language

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.