llama-cpp-python CUDA Installation for ComfyUI PortableThis guide helps you install llama-cpp-python with GPU (CUDA) support for ComfyUI’s Windows portable version.
C:\ComfyUI_windows_portable\python_embededcmd and press Enter.Make sure the installation script is saved here:
.\ComfyUI\custom_nodes\ComfyUI-JoyCaption\install_llama_official.py
In the command prompt (opened in step 1), run the script with:
.\python_embeded\python.exe llama_cpp_install.py
The script will:
🕒 This process may take 5–20+ minutes depending on your system.
.\python.exe -m pip install --upgrade pip
.\python.exe -m pip cache purge
.\python.exe -m pip install scikit-build-core cmake
llama-cpp-python set CMAKE_ARGS="-DGGML_CUDA=on" && .\python.exe -m pip install llama-cpp-python --no-cache-dir && set CMAKE_ARGS=
Ctrl+F5 or Cmd+Shift+R).