Anemll/Anemll

Accelerates LLM porting to Apple Neural Engine

View on index · View in 3D Map

Related repos

• Trains neural networks on Apple Neural Engine via private APIs
• LLM inference server for Apple Silicon
• open-source memory engine for LLMs and AI agents
• Fine-tunes LLMs on Apple Silicon
• Runs large language models on iOS and macOS
• Memory system for LLM agents
• run local LLMs fast on your Mac with Swift and MLX
• Fine-tunes LLMs on Apple silicon
• run large language models on any device
• Minimal vLLM engine for fast offline LLM inference with a clean Python codebase