The llama.cpp project has released version b9821, which introduces command-line interface updates allowing users to invoke --version, --licenses, and --help flags. This release provides a comprehensive set of pre-built binaries for macOS, Linux, Android, Windows, and openEuler across various hardware accelerators.
- The app now supports --version, --licenses, and --help CLI arguments (PR #25054).
- macOS builds include Apple Silicon (arm64) and Intel (x64), while iOS XCFrameworks are available.
- Linux binaries cover Ubuntu x64/arm64/s390x CPU, Vulkan, ROCm 7.2, OpenVINO, and SYCL FP32/FP16.
- Windows releases feature CPU, CUDA 12/13, Vulkan, OpenVINO, SYCL, HIP, and OpenCL Adreno variants.
- Android arm64 (CPU) binaries are provided, alongside a general UI package.
This update ensures compatibility with the latest hardware backends and improves CLI usability for developers deploying llama.cpp across diverse environments.