llama.cpp b10011 refactors server prompt cache state ownership

The llama.cpp project released build b10011, which includes a refactor of the server's prompt cache state ownership. This update moves prompt state data to the `server_prompt_cache` and ensures checkpoints are cleared upon prompt clear.

• Server: handle batched slot being cleared
• macOS/iOS: builds for Apple Silicon (arm64), Intel (x64), and iOS XCFramework; KleidiAI on Apple Silicon is disabled
• Linux: binaries for Ubuntu x64/arm64/s390x CPU, Vulkan, ROCm 7.2, OpenVINO, and SYCL FP32/FP16
• Android: arm64 CPU binary
• Windows: CPU, OpenCL Adreno, CUDA 12/13, Vulkan, OpenVINO, SYCL, and HIP binaries
• openEuler: x86 and aarch64 builds for 310p and 910b (ACL Graph); x86 build disabled
• UI: standard UI binary