llama.cpp b11268 adds ROCm 10 and Snapdragon support

llama.cpp has released build b11268, expanding hardware support to include ROCm 10.0 for AMD GPUs on Linux and Windows, as well as native Snapdragon support for Linux devices. The update also provides CUDA 13 builds (13.4 libraries) alongside existing CUDA 12 options across multiple operating systems. Additionally, OpenVINO and SYCL backends are available for Intel hardware, while macOS KleidiAI builds have been temporarily disabled in this release. This update significantly broadens the range of consumer and enterprise hardware capable of running local LLMs efficiently.