A framework for building native applications using React

Build cross-platform desktop apps with JavaScript, HTML, and CSS

LLM inference in C/C++

Protocol Buffers - Google's data interchange format

Port of OpenAI's Whisper model in C/C++

📚 C/C++ 技术面试基础知识总结，包括语言、程序库、数据结构、算法、系统、网络、链接装载库等知识及面试经验、招聘、内推等信息。This repository is a summary of the basic knowledge of recruiting job seekers and beginners in the direction of C/C++ technology, in…

Distribute and run LLMs with a single file.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

A framework for building native Windows apps with React.

Tensor library for machine learning

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

CUDA Templates and Python DSLs for High-Performance Linear Algebra

High-speed Large Language Model Serving for Local Deployment

The C++ REST SDK is a Microsoft project for cloud-based client-server communication in native code using a modern asynchronous C++ API design. This project aims to help C++ developers connect to an…

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

Tomahawk, the multi-source music player

Local AI API Platform

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

[not maintained] Lightweight JavaScript library operating system for the cloud

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

🍻 A Toast popup plugin for your fancy Cordova app

An ISP Pipeline For HDR CMOS Image Sensor

An open-source image signal processing (ISP) pipeline implemented by C++

vortex backend