llamacpp_python/cuda/Containerfile

FROM quay.io/opendatahub/workbench-images:cuda-ubi9-python-3.9-20231206
USER root
RUN  dnf install -y gcc-toolset-13-gcc gcc-toolset-13-gcc-c++
USER 1001
WORKDIR /locallm
COPY src .
ENV CMAKE_ARGS="-DGGML_CUDA=on -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DLLAMA_F16C=OFF"
ENV FORCE_CMAKE=1
RUN CC="/opt/rh/gcc-toolset-13/root/usr/bin/gcc" CXX="/opt/rh/gcc-toolset-13/root/usr/bin/g++" pip install --no-cache-dir -r ./requirements.txt
ENTRYPOINT [ "sh", "run.sh" ]