llama.cpp Hits v1.0.0 After 3.5 Years — Local AI Gets Semantic Versioning
The twice-postponed milestone arrived on November 13: llama.cpp v1.0.0 and ggml v1.0.0, the first stable releases of the C/C++ engine that made running open models on ordinary hardware normal. The headline is a promise, not a feature — both libraries now follow semantic versioning, so breaking changes to the public C API in ./include come with a major bump. The engine supports more than 150 model architecture variants and all mainstream speculative decoding methods, and ships through Docker, Debian, Homebrew, conda-forge, MacPorts, Winget and an XCFramework for iOS and macOS.