node-llama-cpp
Discover the local deployment of large language models that supports Metal, CUDA, and Vulkan. With pre-built binaries and easy source build fallback, it works without node-gyp or Python. It adapts to various hardware configurations automatically and offers CLI interaction without coding. Stay current with the latest llama.cpp releases and enable functionality like JSON schema adherence or function calling. Perfect for developers, it includes embedding capabilities, TypeScript support, and extensive documentation.