# Multi-stage Dockerfile
ARG BASE_IMAGE=nvcr.io/nvidia/pytorch
ARG BASE_TAG=24.05-py3
ARG DEVEL_IMAGE=devel

FROM ${BASE_IMAGE}:${BASE_TAG} as base

# https://www.gnu.org/software/bash/manual/html_node/Bash-Startup-Files.html
# The default values come from `nvcr.io/nvidia/pytorch`
ENV BASH_ENV=${BASH_ENV:-/etc/bash.bashrc}
ENV ENV=${ENV:-/etc/shinit_v2}
SHELL ["/bin/bash", "-c"]

FROM base as devel

COPY docker/common/install_base.sh install_base.sh
RUN bash ./install_base.sh && rm install_base.sh

COPY docker/common/install_cmake.sh install_cmake.sh
RUN bash ./install_cmake.sh && rm install_cmake.sh

COPY docker/common/install_ccache.sh install_ccache.sh
RUN bash ./install_ccache.sh && rm install_ccache.sh

# Only take effect when the base image is 12.4.0-devel-centos7.
COPY docker/common/install_cuda_toolkit.sh install_cuda_toolkit.sh
RUN bash ./install_cuda_toolkit.sh && rm install_cuda_toolkit.sh

# Download & install internal TRT release
ARG TRT_VER
ARG CUDA_VER
ARG CUDNN_VER
ARG NCCL_VER
ARG CUBLAS_VER
COPY docker/common/install_tensorrt.sh install_tensorrt.sh
RUN bash ./install_tensorrt.sh \
    --TRT_VER=${TRT_VER} \
    --CUDA_VER=${CUDA_VER} \
    --CUDNN_VER=${CUDNN_VER} \
    --NCCL_VER=${NCCL_VER} \
    --CUBLAS_VER=${CUBLAS_VER} && \
    rm install_tensorrt.sh

# Install latest Polygraphy
COPY docker/common/install_polygraphy.sh install_polygraphy.sh
RUN bash ./install_polygraphy.sh && rm install_polygraphy.sh

# Install mpi4py
COPY docker/common/install_mpi4py.sh install_mpi4py.sh
RUN bash ./install_mpi4py.sh && rm install_mpi4py.sh

# Install PyTorch
ARG TORCH_INSTALL_TYPE="skip"
COPY docker/common/install_pytorch.sh install_pytorch.sh
RUN bash ./install_pytorch.sh $TORCH_INSTALL_TYPE && rm install_pytorch.sh

FROM ${DEVEL_IMAGE} as wheel
WORKDIR /src/tensorrt_llm
COPY benchmarks benchmarks
COPY cpp cpp
COPY benchmarks benchmarks
COPY scripts scripts
COPY tensorrt_llm tensorrt_llm
COPY 3rdparty 3rdparty
COPY setup.py requirements.txt requirements-dev.txt ./

# Create cache directories for pip and ccache
RUN mkdir -p /root/.cache/pip /root/.cache/ccache
ENV CCACHE_DIR=/root/.cache/ccache
# Build the TRT-LLM wheel
ARG BUILD_WHEEL_ARGS="--clean --trt_root /usr/local/tensorrt --python_bindings --benchmarks"
RUN --mount=type=cache,target=/root/.cache/pip --mount=type=cache,target=/root/.cache/ccache \
    python3 scripts/build_wheel.py ${BUILD_WHEEL_ARGS}

FROM ${DEVEL_IMAGE} as release

# Create a cache directory for pip
RUN mkdir -p /root/.cache/pip

WORKDIR /app/tensorrt_llm
COPY --from=wheel /src/tensorrt_llm/build/tensorrt_llm*.whl .
RUN --mount=type=cache,target=/root/.cache/pip \
    pip install tensorrt_llm*.whl --extra-index-url https://pypi.nvidia.com && \
    rm tensorrt_llm*.whl
COPY README.md ./
COPY docs docs
COPY cpp/include include
RUN ln -sv $(python3 -c 'import site; print(f"{site.getsitepackages()[0]}/tensorrt_llm/bin")') bin && \
    test -f bin/executorWorker && \
    ln -sv $(python3 -c 'import site; print(f"{site.getsitepackages()[0]}/tensorrt_llm/libs")') lib && \
    test -f lib/libnvinfer_plugin_tensorrt_llm.so && \
    ln -sv lib/libnvinfer_plugin_tensorrt_llm.so lib/libnvinfer_plugin_tensorrt_llm.so.9 && \
    echo "/app/tensorrt_llm/lib" > /etc/ld.so.conf.d/tensorrt_llm.conf && \
    ldconfig
ARG SRC_DIR=/src/tensorrt_llm
COPY --from=wheel ${SRC_DIR}/benchmarks benchmarks
ARG CPP_BUILD_DIR=${SRC_DIR}/cpp/build
COPY --from=wheel \
     ${CPP_BUILD_DIR}/benchmarks/bertBenchmark \
     ${CPP_BUILD_DIR}/benchmarks/gptManagerBenchmark \
     ${CPP_BUILD_DIR}/benchmarks/gptSessionBenchmark \
     benchmarks/cpp/
COPY examples examples
RUN chmod -R a+w examples && \
    rm -v \
      benchmarks/cpp/bertBenchmark.cpp \
      benchmarks/cpp/gptManagerBenchmark.cpp \
      benchmarks/cpp/gptSessionBenchmark.cpp \
      benchmarks/cpp/CMakeLists.txt
ARG GIT_COMMIT
ARG TRT_LLM_VER
ENV TRT_LLM_GIT_COMMIT=${GIT_COMMIT} \
    TRT_LLM_VERSION=${TRT_LLM_VER}