llama.cpp version b9724 includes several bug fixes and improvements, such as build fixes, overflow avoidance in area() function, and a sanity check in get_u32(). The release provides pre-built binaries for macOS (arm64 and x64), Linux (x64, arm64, s390x, Vulkan, ROCm, OpenVINO, SYCL), Android (arm64), Windows (x64, arm64, CUDA 12/13, Vulkan, OpenVINO, SYCL, HIP), and openEuler (x86 and aarch64 with ACL Graph support), along with a UI package.