llama.cpp and ggml reach v1.0.0 with a stable API promise

The llama.cpp team released version 1.0.0 of the llama.cpp inference library and the ggml tensor library it is built on, announced on Hugging Face. From this release onward both projects follow semantic versioning: a major version bump marks a breaking change to the public C API in their include directories, while minor releases cover backward-compatible features, backend updates and new model support. The libraries are distributed as pre-release artifacts for Linux, macOS, Windows, Android and iOS, and through Docker, Homebrew, conda-forge, MacPorts, Winget and an XCFramework. The team says llama.cpp supports more than 150 model architecture variants and all mainstream speculative decoding methods.