llama.cpp b9947 adds --output CLI option and new binaries

The llama.cpp project has released version b9947, introducing a new `--output` command-line interface option. This update also provides pre-built binaries for macOS, iOS, Linux, Android, Windows, and openEuler platforms.

• The CLI now supports the `--output` flag to control output behavior.
• macOS Apple Silicon builds with KleidiAI are disabled in this release.
• New binaries include Ubuntu x64 (CPU), arm64 (CPU), s390x (CPU), Vulkan, ROCm 7.2, OpenVINO, and SYCL FP32/FP16 variants.
• Windows builds now support CUDA 13 alongside CUDA 12, as well as HIP and OpenCL Adreno.
• openEuler x86 (310p), x86 (910b with ACL Graph), and aarch64 (310p, 910b with ACL Graph) binaries are available.

This release expands hardware support for various accelerators and provides users with updated tools for running llama.cpp across diverse operating systems and architectures.