llama.cpp b10012 release fixes hexagon queue signal and provides binaries for multiple platforms

The llama.cpp project has released version b10012, which includes a fix for the hmx-queue signal enum-narrowing problem on Hexagon architectures.

This update provides pre-built binaries across several operating systems and hardware configurations:

• macOS Apple Silicon (arm64) and Intel (x64), with KleidiAI disabled for Apple Silicon.
• Linux distributions including Ubuntu x64, arm64, s390x, and variants supporting Vulkan, ROCm 7.2, OpenVINO, and SYCL (FP32/FP16).
• Windows builds for CPU, OpenCL Adreno, CUDA 12.4, CUDA 13.3, Vulkan, OpenVINO, SYCL, and HIP.
• Android arm64 (CPU) support.
• openEuler x86 and aarch64 builds using ACL Graph, with standard openEuler support disabled.
• A standalone UI package is also available.

The release ensures compatibility across diverse hardware backends while addressing specific signal handling issues in the Hexagon implementation.