The llama.cpp project released version b10007, which includes a fix for an OpenCL bug related to the `cl_khr_integer_dot_product` extension. The update ensures that the backend initialization does not fail on devices lacking this extension and prevents the calling of dp4 kernels when dot product support is unavailable.

This release provides binaries for macOS (Apple Silicon and Intel), iOS, Linux (CPU, Vulkan, ROCm, OpenVINO, SYCL), Android, Windows (CPU, CUDA 12/13, Vulkan, OpenVINO, SYCL, HIP), and openEuler.

The update allows users to run llama.cpp on a wider range of hardware configurations without encountering initialization errors due to missing OpenCL integer dot product support.