PF4Public@users.noreply.github.com ggml-org/llama.cpp https://github.com/ggml-org/llama.cpp/issues Allow the build to download the npm registry (live ebuild only, needed by the webui flag) Enable the NVIDIA CUDA GPU backend Build the example programs Enable the AMD ROCm/HIP GPU backend Enable the OpenBLAS backend Enable the OpenCL backend Use OpenMP in the CPU backend Use OpenSSL for HTTPS model downloads Enable the RPC backend for distributed inference Link against the installed sci-ml/ggml instead of the bundled copy; the CPU ISA set and the backends are then selected by ggml's own USE flags Enable the Vulkan backend Embed the prebuilt web UI in llama-server