The llama.cpp project has released version b9884, which includes a fix for a 32-bit integer overflow in the CEIL_DIV function within the Vulkan backend.

  • macOS Apple Silicon (arm64) binaries are available, while KleidiAI support is disabled.
  • Linux builds cover Ubuntu x64 and arm64 CPU, s390x CPU, Vulkan, ROCm 7.2, OpenVINO, and SYCL FP32/FP16.
  • Android arm64 CPU binaries are provided.
  • Windows builds include CPU, OpenCL Adreno, CUDA 12/13, Vulkan, OpenVINO, SYCL, and HIP variants.
  • openEuler support is partially disabled, with specific builds for x86 and aarch64 architectures available.
  • A standalone UI binary is also included in the release.