# llama.cpp and ggml release v1.0.0 with semantic versioning rules

published: 2026-11-13T16:05:28.289Z
topic: infrastructure
source: https://huggingface.co/blog/ggml-org/llama-cpp-v1
url: https://aiagentnews.io/stories/llama-cpp-and-ggml-release-v1-0-0-with-semantic-versioning-rules

The llama.cpp and ggml projects have released version 1.0.0, with their libraries now marking API and ABI incompatibilities through major-version bumps. The team says downstream developers can rely on the public headers and should expect stricter version boundaries going forward.

The llama.cpp team at Hugging Face released libraries v1.0.0 for llama.cpp, which provides LLM inference in C/C++ through libllama, and for ggml, a tensor library exposed through libggml. Public headers live in llama.cpp/include/ and ggml/include/. The team says the project has existed for 3.5 years and that many downstream applications already depend on it.

Under the new rules, a breaking change to the public C API in ./include triggers a MAJOR bump, while backward-compatible features, backend updates, model support and API additions trigger a MINOR bump. Bug fixes with no API change trigger a PATCH bump. The team says it will be stricter about making those boundaries visible to downstream consumers.

Distribution channels listed include pre-release artifacts for Linux, macOS, Windows, Android and iOS, plus Docker, Debian, Homebrew, conda-forge, MacPorts, Winget and XCFramework. The project also says llama.cpp supports more than 150 architecture variants and all mainstream speculative decoding methods.

## Why it matters if you build agents

If you embed libllama or libggml, a MAJOR version change now signals a public C API or ABI break, so you can pin to a major version and upgrade deliberately. Minor and patch releases are meant to stay backward compatible.

Pin your dependency to the major version you tested against and check the release notes before moving to a new major release.
