The llama.cpp project has released version b10054, which includes a documentation note regarding the use of OpenCL with the Adreno 810 GPU.

  • macOS Apple Silicon (arm64) binaries are available, while KleidiAI support is disabled.
  • Linux builds cover Ubuntu x64 and arm64 for CPU, Vulkan, ROCm 7.2, OpenVINO, and SYCL FP32/FP16.
  • Android arm64 (CPU) binaries are provided.
  • Windows builds include CPU, Vulkan, OpenVINO, SYCL, HIP, and CUDA 12/13 variants.
  • openEuler support for x86 and aarch64 architectures is listed, with some configurations disabled.

This release provides updated binaries across major operating systems and hardware accelerators for local inference.