llama.cpp b10002 adds ggml contiguity checks and releases binaries for macOS, Linux, Windows, Android

The llama.cpp project has released version b10002, which includes a new set of functions in ggml for checking the contiguity of inner tensor dimensions. This build is available across multiple platforms and hardware accelerators.

• macOS Apple Silicon (arm64) and Intel (x64) binaries are provided, with KleidiAI support disabled.
• Linux builds cover Ubuntu x64, arm64, and s390x for CPU, as well as Vulkan, ROCm 7.2, OpenVINO, and SYCL variants.
• Windows releases include CPU, OpenCL Adreno, CUDA 12/13, Vulkan, OpenVINO, SYCL, and HIP support.
• Android arm64 (CPU) binaries are also included.
• openEuler builds for x86 and aarch64 architectures are available, with some configurations marked as disabled.

The release provides updated binaries for developers requiring specific hardware acceleration or platform compatibility.