Tiny YOLO for iOS implemented using CoreML but also using the new MPS graph API.

ENFUGUE is an open-source web app for making studio-grade images and video using generative AI.

Run LLaMA (and Stanford-Alpaca) inference on Apple Silicon GPUs.

Qwen Image models through MPS

A Julia package dedicated to simulating quantum many-body systems using Matrix Product States (MPS)

A few quick scripts focused on testing TensorFlow/PyTorch/Llama 2 on macOS.

Port of Facebook's LLaMA (Large Language Model Meta AI) in Golang with embedded C/C++

Making parliamentary voting information accessible, understandable, and easy to use so that you can hold your elected representatives to account.

Tensor network machine learning. Based on the paper "Supervised Learning with Quantum Inspired Tensor Networks" http://arxiv.org/abs/1605.05775

Glasses detection, classification and segmentation

A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)

A pedagogical realization of MPS method.

MPS is a high-performance HTTP(S) proxy library that supports forward proxies, reverse proxies, man-in-the-middle proxies, tunnel proxies, Websocket proxies. MPS 是一个高性能HTTP(s)中间代理库，它支持正向代理、反向代理、中间人代理、隧道代理、Websocket代理

Incremental Program Analysis Framework

VGGT 3D Vision Agent optimized for Apple Silicon with Metal Performance Shaders

Experimental fork of Facebooks LLaMa model which runs it with GPU acceleration on Apple Silicon M1/M2

Extended HE AAC Encoder and Decoder. Contact: mob-audio@ittiam.com

Playing with Metal

A flexible MPS framework

telegram bot for self-hosted local inference of stable diffusion, text-to-speech and large language models, such as llama3