MetamorphicPhoenix / requirements.txt
Basementup's picture
Fix CUDA runtime libs for llama-cpp on ZeroGPU
d57db80 verified
Raw History Blame
365 Bytes
gradio
spaces
huggingface_hub>=0.30.0
# CUDA wheel for ZeroGPU (no local nvcc build)
--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124
llama-cpp-python
# CUDA 12 runtime libs the llama-cpp cu124 wheel links against (libcudart.so.12, libcublas*.so.12)
nvidia-cuda-runtime-cu12
nvidia-cublas-cu12
requests
gTTS
pypdf
PyPDF2
python-docx
reportlab