Dockerfile.cli.cuda

FROM rust:1.78.0 as build
# Copy the files in your machine to the Docker image
WORKDIR /app
COPY . .

# Remove lantern_extras from workspace
RUN rm -rf lantern_extras && sed -i -e 's/"lantern_extras",//' Cargo.toml

ENV CC=/usr/bin/clang-18
ENV CXX=/usr/bin/clang++-18
# Build your program for release
RUN apt update && \
  apt install -y --no-install-recommends lsb-release wget software-properties-common gnupg pkg-config curl libssl-dev && \
  curl -s https://apt.llvm.org/llvm.sh | bash -s -- 18 && \
  cargo build --release --package lantern_cli

FROM nvcr.io/nvidia/cuda:11.8.0-runtime-ubuntu22.04
COPY --from=build /app/target/release/lantern-cli .
RUN apt update && \
  apt install -y wget && apt clean
# Download onnxruntime
RUN mkdir -p /usr/local/lib && \
    cd /usr/local/lib && \
    wget -q https://github.com/microsoft/onnxruntime/releases/download/v1.16.1/onnxruntime-linux-x64-gpu-1.16.1.tgz && \
    tar xzf ./onnx*.tgz && \
    rm -rf ./onnx*.tgz && \
    mv ./onnx* ./onnxruntime 

# Install libcudnn
RUN wget -q https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/libcudnn8_8.7.0.84-1+cuda11.8_amd64.deb -O libcudnn.deb && \
    dpkg -i libcudnn.deb && \
    rm -rf libcudnn.deb

RUN ln -s /usr/local/cuda/targets/x86_64-linux/lib/libnvrtc.so.11.2 /usr/local/cuda/targets/x86_64-linux/lib/libnvrtc.so
ENV ORT_STRATEGY=system
ENV ORT_DYLIB_PATH=/usr/local/lib/onnxruntime/lib/libonnxruntime.so
# Run the binary
ENTRYPOINT ["./lantern-cli"]