wizard-mega-ggml / requirements.txt
winglian's picture
Duplicate from openaccess-ai-collective/ggml-ui
bd8cd88
raw
history blame
251 Bytes
--extra-index-url https://pypi.ngc.nvidia.com
nvidia-cuda-runtime
nvidia-cublas
llama-cpp-python @ https://github.com/OpenAccess-AI-Collective/ggml-webui/releases/download/v0.1.50-rc3/llama_cpp_python-gpu-0.1.50-cp38-cp38-linux_x86_64.whl
pyyaml
torch