Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

The open source coding agent.

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

Runs 405B LLMs on 8GB VRAM

dLLM: Simple Diffusion Language Modeling

Cost-efficient and pluggable Infrastructure components for GenAI inference

CMS Offline Software

Seamless operability between C++11 and Python

✨ Python library and CLI to upload photo and video on Instagram. W/o a phone!