llama.cpp hits v1.0.0
The popular library for running AI models locally gets its first major stable release.

Georgi Gerganov announced on Friday that llama.cpp v1.0.0 is now available.
Hugging Face CEO Clement Delangue called it the first major, fully stable version of the most used library for running AI models locally, on phones, laptops and workstations.
Delangue said the release means people can run AI without sending their data to anyone. Gerganov's post had about 1,500 likes.



