The llama.cpp project has released version b9918, which includes the addition of a `set_rows` function with `src0 f16` support via pull request #25434. This update is co-authored by Georgi Gerganov.

  • macOS Apple Silicon (arm64) binaries are available, while KleidiAI support remains 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 releases include CPU, OpenCL Adreno, CUDA 12/13, Vulkan, OpenVINO, SYCL, and HIP variants.
  • openEuler support for x86 and aarch64 architectures is listed, with some configurations disabled.
  • A standalone UI binary is also included in the release.