GGML and llama.cpp join HF to ensure the long-term progress of Local AI

GGML, the creators of the popular llama.cpp library, are officially joining Hugging Face to advance the progress of local AI. This collaboration aims to provide long-term resources and support for the open-source community behind these projects. The technical focus will be on seamlessly integrating Hugging Face's `transformers` library with `llama.cpp` to simplify deploying new models for local inference. Ultimately, the shared vision is to build an efficient inference stack that makes open-source AI accessible on personal devices.