The llama.cpp team at Hugging Face released llama.cpp v1.0.0 and ggml v1.0.0 on Nov. 13, the team said. llama.cpp is a C/C++ engine for running LLMs on hardware from consumer machines to enterprise servers, and ggml is the tensor library underneath it.[1] Hugging Face said that moving forward, both llama.cpp and ggml will reflect API and ABI incompatibilities with major-version bumps.[1] In the 3.5 years since it started, llama.cpp has added support for more than 150 model architecture variants, and many downstream applications already depend on it.[1] For developers building on these libraries, Hugging Face says that moving forward, both llama.cpp and ggml will reflect API and ABI incompatibilities with major-version bumps.[1]