FROM nvidia/cuda:11.2.1-base-ubuntu20.04

LABEL maintainer="Amazon AI"
LABEL dlc_major_version="1"

ARG PYTHON=python3.8
ARG PYTHON_PIP=python3-pip
ARG PIP=pip3
ARG PYTHON_VERSION=3.8.9

ARG TFS_SHORT_VERSION=2.7
ARG TFS_URL=https://framework-binaries.s3.us-west-2.amazonaws.com/tensorflow_serving/r2.7_aws/gpu/tensorflow_model_server

ENV NVIDIA_REQUIRE_CUDA="cuda>=11.2 brand=tesla,driver>=418,driver<419 brand=tesla,driver>=440,driver<441 driver>=450"
ENV NCCL_VERSION=2.8.4-1+cuda11.2
ENV CUDNN_VERSION=8.1.0.77-1+cuda11.2

# See http://bugs.python.org/issue19846
ENV LANG=C.UTF-8
ENV PYTHONDONTWRITEBYTECODE=1
# Python won’t try to write .pyc or .pyo files on the import of source modules
ENV PYTHONUNBUFFERED=1
ENV MODEL_BASE_PATH=/models
# The only required piece is the model name in order to differentiate endpoints
ENV MODEL_NAME=model
# Fix for the interactive mode during an install in step 21
ENV DEBIAN_FRONTEND=noninteractive

# allow unauthenticated and allow downgrades for special libcublas library
RUN apt-get update \
 && apt-get install -y --no-install-recommends --allow-unauthenticated --allow-downgrades\
    ca-certificates \
    cuda-command-line-tools-11-2 \
    cuda-nvrtc-11-2 \
    cuda-nvrtc-dev-11-2 \
    cuda-cudart-dev-11-2 \
    libcufft-dev-11-2 \
    libcurand-dev-11-2 \
    libcusolver-dev-11-2 \
    libcusparse-dev-11-2 \
    libbz2-dev \
    liblzma-dev \
    #cuda-cublas-dev not available with 10-1, install libcublas instead
    libcublas-11-2 \
    libcublas-dev-11-2 \
    libcudnn8=${CUDNN_VERSION} \
    libcudnn8-dev=${CUDNN_VERSION} \
    libnccl2=${NCCL_VERSION} \
    libnccl-dev=${NCCL_VERSION}  \
    libgomp1 \
    libffi-dev \
    curl \
    emacs \
    git \
    wget \
    unzip \
    vim \
    build-essential \
    zlib1g-dev \
    openssl \
    libssl1.1 \
    libreadline-gplv2-dev \
    libncursesw5-dev \
    libssl-dev \
    libsqlite3-dev \
    tk-dev \
    libgdbm-dev \
    libc6-dev \
    # remove libsasl2-2 after Nvidia docker upstream fix CVE-2022-24407
    libsasl2-2 \
 && apt-get clean \
 && rm -rf /var/lib/apt/lists/*

# Install python3.8
RUN wget https://www.python.org/ftp/python/$PYTHON_VERSION/Python-$PYTHON_VERSION.tgz \
 && tar -xvf Python-$PYTHON_VERSION.tgz \
 && cd Python-$PYTHON_VERSION \
 && ./configure && make && make install \
 && rm -rf ../Python-$PYTHON_VERSION*

RUN ${PIP} --no-cache-dir install --upgrade \
    pip \
    setuptools


# Install TensorRT 
# see https://github.com/NVIDIA/TensorRT/blob/master/docker/ubuntu-20.04.Dockerfile
ENV TRT_VERSION 8.0.1.6
ENV CUDA_VERSION 11.3.1
RUN v="${TRT_VERSION%.*}-1+cuda${CUDA_VERSION%.*}" &&\
    apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/7fa2af80.pub &&\
    apt-get update &&\
    yes | apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} \
        libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} \
        python3-libnvinfer=${v}


# Some TF tools expect a "python" binary
RUN ln -s $(which ${PYTHON}) /usr/local/bin/python \
 && ln -s $(which ${PIP}) /usr/bin/pip

RUN apt-get update \
 && apt-get -y install --no-install-recommends \
    curl \
    gnupg2 \
 && apt-get clean \
 && rm -rf /var/lib/apt/lists/*

RUN ${PIP} install -U --no-cache-dir \
    "awscli<2" \
    boto3 \
    cython==0.29.21 \
    gevent==21.1.1 \
    requests==2.25.1 \
    grpcio==1.34.1 \
    protobuf==3.15.0 \
# using --no-dependencies to avoid installing tensorflow binary
 && ${PIP} install --no-dependencies --no-cache-dir \
    tensorflow-serving-api-gpu=="2.7.0"

RUN curl $TFS_URL -o /usr/bin/tensorflow_model_server \
 && chmod 555 /usr/bin/tensorflow_model_server

# Expose gRPC and REST port
EXPOSE 8500 8501

# Set where models should be stored in the container
RUN mkdir -p ${MODEL_BASE_PATH}

# Create a script that runs the model server so we can use environment variables
# while also passing in arguments from the docker command line
RUN echo '#!/bin/bash \n\n' > /usr/bin/tf_serving_entrypoint.sh \
 && echo '/usr/bin/tensorflow_model_server --port=8500 --rest_api_port=8501 --model_name=${MODEL_NAME} --model_base_path=${MODEL_BASE_PATH}/${MODEL_NAME} "$@"' >> /usr/bin/tf_serving_entrypoint.sh \
 && chmod +x /usr/bin/tf_serving_entrypoint.sh

COPY deep_learning_container.py /usr/local/bin/deep_learning_container.py

RUN chmod +x /usr/local/bin/deep_learning_container.py

RUN HOME_DIR=/root \
 && curl -o ${HOME_DIR}/oss_compliance.zip https://aws-dlinfra-utilities.s3.amazonaws.com/oss_compliance.zip \
 && unzip ${HOME_DIR}/oss_compliance.zip -d ${HOME_DIR}/ \
 && cp ${HOME_DIR}/oss_compliance/test/testOSSCompliance /usr/local/bin/testOSSCompliance \
 && chmod +x /usr/local/bin/testOSSCompliance \
 && chmod +x ${HOME_DIR}/oss_compliance/generate_oss_compliance.sh \
 && ${HOME_DIR}/oss_compliance/generate_oss_compliance.sh ${HOME_DIR} ${PYTHON} \
 && rm -rf ${HOME_DIR}/oss_compliance*

RUN curl https://aws-dlc-licenses.s3.amazonaws.com/tensorflow-2.7/license.txt -o /license.txt

CMD ["/usr/bin/tf_serving_entrypoint.sh"]