The ggml-org project has released commit b9981 of llama.cpp, which includes an update to the cpp-httplib library version 0.50.1.

  • macOS Apple Silicon builds are available for arm64 architectures.
  • Linux binaries support Ubuntu x64, arm64, and s390x CPUs, as well as Vulkan, ROCm 7.2, OpenVINO, and SYCL backends.
  • Android arm64 CPU builds are provided.
  • Windows releases cover CPU, OpenCL Adreno, CUDA 12/13, Vulkan, OpenVINO, SYCL, and HIP.
  • openEuler support includes x86 and aarch64 builds for 310p and 910b processors using ACL Graph.
  • A standalone UI package is also included in the release.