lucascs@proton.me Lucas C.S. KoboldCpp is a local AI server built on ggml/llama.cpp that bundles LLM text generation (the KoboldAI Lite web UI plus an OpenAI-compatible API), Stable Diffusion image generation, Whisper speech-to-text and TTS behind a single pure-Python launcher. This ebuild builds the ggml backends from source and installs the launcher (koboldcpp.py) together with the embedded web UI and resources. It ships neither the upstream PyInstaller binary nor any model weights, and it deletes the prebuilt helper binaries the source tarball carries for Windows so that no executable blob is installed. The CPU backend is built portable rather than tuned to the build host, and its x86 instruction set is selected through CPU_FLAGS_X86: upstream offers three tiers (AVX2+FMA+F16C, AVX only, SSE3 only). GPU acceleration is optional in every direction - Vulkan (upstream's officially supported path for both AMD and NVIDIA), CUDA/cuBLAS, and ROCm/hipBLAS - and a CPU-only build works with all of them disabled. Build the CUDA/cuBLAS backend (koboldcpp_cublas) for NVIDIA GPUs, for every architecture the installed toolkit supports Build the ROCm/hipBLAS backend (koboldcpp_hipblas) for AMD GPUs, for the architectures selected in AMDGPU_TARGETS Build the Vulkan backend (koboldcpp_vulkan), upstream's officially supported GPU path for both AMD and NVIDIA LostRuins/koboldcpp https://github.com/LostRuins/koboldcpp/issues https://github.com/LostRuins/koboldcpp/releases