Explore live open-source projects and AI models.

Apple Neural Engine (ANE) LLM inference engine — reverse-engineered private APIs, Metal GPU shaders, hybrid ANE+GPU+CPU on Apple Silicon. 32 tok/s matching llama.cpp, 3.6 TFLOPS fused ANE mega-kernels.

Box execute is a npm package to compile/run codes (c,cpp,python) in a virtualized environment, Here virtualized environment used is a docker container. This packages is built to ease the task of running a code against test cases as done by websites used to practice algorithmic coding.

基于官方yolov8的onnxruntime的cpp例子修改，目前已经支持图像分类、目标检测、实例分割。Based on the cpp example modification of official yolov8's onnxruntime, it currently supports image classification, target detection, and instance segmentation.

http://snowkit.github.io/linc/ Haxe @:native bindings for Vulkan. Vulkan is a low-level graphics API by Khronos Group. This repository contains Haxe/CPP bindings for the Vulkan API.

An easy cpp json package

A simple inference web UI for llama.cpp / lama-cpp-python

Run llama.cpp server with Vulkan

Reboot of the attempt to port Three.cpp

Experimental interface environment for open source LLM, designed to democratize the use of AI. Powered by llama-cpp, llama-cpp-python and Gradio.

C++11 as a scripting language, using CMake as a build system