The llama.cpp project has released version b10015, which includes a specific fix for OpenCL by avoiding the use of `clCreateBufferWithProperties` when targeting CL 2.x.

  • macOS Apple Silicon builds are available in standard and KleidiAI-enabled variants, though the latter is now disabled.
  • Linux binaries support CPU (x64, arm64, s390x), Vulkan, ROCm 7.2, OpenVINO, and SYCL (FP32/FP16).
  • Windows builds include CPU, OpenCL Adreno, CUDA 12/13, Vulkan, OpenVINO, SYCL, and HIP.
  • Android arm64 (CPU) and iOS XCFramework binaries are also provided.
  • openEuler support is partially disabled, with specific ACL Graph builds for x86 and aarch64 architectures remaining available.