llama.cpp b10064 release with OpenCL transpose optimization

The llama.cpp project has released version b10064, which includes a change to the OpenCL backend. This update modifies the q4_K quantization format by transposing noshuffle scales to enable coalesced reads.

• The release provides binaries for macOS (Apple Silicon and Intel), Linux (Ubuntu x64, arm64, s390x), Windows (CPU, CUDA 12/13, Vulkan, ROCm, SYCL, HIP), Android, and iOS.
• OpenCL Adreno support is available for Windows arm64.
• KleidiAI support on macOS Apple Silicon remains disabled in this build.
• The update addresses performance by optimizing memory access patterns for specific quantization layers.