Create an environment with conda:
conda create -n llama python=3.9
conda activate llama
Install the requirements:
pip install -r requirements.txt
Install llama-cpp-python with cuLAB (from this link):
CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install --upgrade --force-reinstall llama-cpp-python --no-cache-dir