Dockerfile.neuron

FROM ubuntu:20.04

LABEL maintainer="Amazon AI"
LABEL dlc_major_version="1"
# Specify LABEL for inference pipelines to use SAGEMAKER_BIND_TO_PORT
# https://docs.aws.amazon.com/sagemaker/latest/dg/inference-pipeline-real-time.html
LABEL com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true


# Define framework-related package sources
ARG PYTHON=python3
ARG PYTHON_PIP=python3-pip
ARG PIP=pip3
ARG PYTHON_VERSION=3.8.16
ARG TFS_SHORT_VERSION=1.15.5
ARG TF_S3_URL=https://tensorflow-aws.s3-us-west-2.amazonaws.com

# Prevent docker build get stopped by requesting user interaction
ENV DEBIAN_FRONTEND=noninteractive
ENV DEBCONF_NONINTERACTIVE_SEEN=true
# Set environment variables for MKL
# https://www.tensorflow.org/performance/performance_guide#tensorflow_with_intel%C2%AE_mkl_dnn
ENV KMP_AFFINITY=granularity=fine,compact,1,0
ENV KMP_BLOCKTIME=1
ENV KMP_SETTINGS=0
# Python won’t try to write .pyc or .pyo files on the import of source modules
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1
# See http://bugs.python.org/issue19846
ENV PYTHONIOENCODING=UTF-8
ENV LANG=C.UTF-8
ENV LC_ALL=C.UTF-8
# Specify the location of module that contains the training logic for SageMaker
# https://docs.aws.amazon.com/sagemaker/latest/dg/docker-container-environmental-variables-entrypoint.html
ENV SAGEMAKER_TFS_VERSION="${TFS_SHORT_VERSION}"
ENV PATH="$PATH:/sagemaker"
ENV LD_LIBRARY_PATH='/usr/local/lib:$LD_LIBRARY_PATH'
ENV MODEL_BASE_PATH=/models
# The only required piece is the model name in order to differentiate endpoints
ENV MODEL_NAME=model

RUN apt-get update \
 && apt-get upgrade -y \
 && apt-get install -y --no-install-recommends \
    build-essential \
    ca-certificates \
    curl \
    emacs \
    git \
    gnupg2 \
    libssl1.1 \
    openssh-client \
    openssh-server \
    openssl \
    vim \
    wget \
    unzip \
    zlib1g-dev \
 && curl -s http://nginx.org/keys/nginx_signing.key | apt-key add - \
 && echo 'deb http://nginx.org/packages/ubuntu/ focal nginx' >> /etc/apt/sources.list \
 && apt-get update \
 && apt-get -y install --no-install-recommends \
    nginx=1.20.1* \
    nginx-module-njs=1.20.1* \
 && rm -rf /var/lib/apt/lists/* \
 && apt-get clean

# SSH login fix. Otherwise user is kicked off after login
RUN sed 's@session\s*required\s*pam_loginuid.so@session optional pam_loginuid.so@g' -i /etc/pam.d/sshd

# Create SSH key.
RUN mkdir -p /root/.ssh/ \
 && mkdir -p /var/run/sshd \
 && ssh-keygen -q -t rsa -N '' -f /root/.ssh/id_rsa \
 && cp /root/.ssh/id_rsa.pub /root/.ssh/authorized_keys \
 && printf "Host *\n  StrictHostKeyChecking no\n" >> /root/.ssh/config

WORKDIR /

RUN apt-get update \
 && apt-get install -y --no-install-recommends \
    libbz2-dev \
    libc6-dev \
    libffi-dev \
    libgdbm-dev \
    libncursesw5-dev \
    libreadline-gplv2-dev \
    libsqlite3-dev \
    libssl-dev \
    libcap-dev \
    tk-dev \
    python3-venv \
    && rm -rf /var/lib/apt/lists/* \
    && apt-get clean

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 \
 && make && make install && rm -rf ../Python-$PYTHON_VERSION* \
 && rm -rf /tmp/tmp*

RUN echo "deb https://apt.repos.neuron.amazonaws.com focal main" > /etc/apt/sources.list.d/neuron.list
RUN wget -qO - https://apt.repos.neuron.amazonaws.com/GPG-PUB-KEY-AMAZON-AWS-NEURON.PUB | apt-key add -
RUN apt-get update

RUN apt-get install -y \
    tensorflow-model-server-neuron=1.15.* \
    aws-neuronx-tools

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

# Some TF tools expect a "python" binary
RUN ln -s $(which python3) /usr/local/bin/python \
 && ln -s $(which pip3) /usr/bin/pip

# cython, falcon, gunicorn, grpc
RUN ${PIP} install --no-cache-dir -U \
    "awscli<2" \
    "pyYAML>=5.4,<5.5" \
    boto3 \
    cython==0.29.21 \
    falcon==2.0.0 \
    gunicorn==20.0.4 \
    gevent==21.1.1 \
    requests==2.25.1 \
    grpcio==1.56.2 \
    protobuf==3.14.0

# pip install statements have been separated out into multiple sequentially executed statements to
# resolve package dependencies during installation.
RUN ${PIP} install tensorflow_serving_api==1.15 --no-deps --extra-index-url https://pip.repos.neuron.amazonaws.com \
 && ${PIP} install "tensorboard-neuron>=1.15,<1.16" --extra-index-url https://pip.repos.neuron.amazonaws.com \
 && ${PIP} install neuron-cc==1.13.* --extra-index-url https://pip.repos.neuron.amazonaws.com \
 && ${PIP} install tensorflow-neuron==1.15.5.2.6.* --extra-index-url https://pip.repos.neuron.amazonaws.com


COPY ./sagemaker /sagemaker


RUN curl ${TF_S3_URL}/MKL-Libraries/libiomp5.so -o /usr/local/lib/libiomp5.so \
 && curl ${TF_S3_URL}/MKL-Libraries/libmklml_intel.so -o /usr/local/lib/libmklml_intel.so


# Expose ports
# gRPC and REST
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/local/bin/entrypoint.sh \
 && echo '/usr/local/bin/tensorflow_model_server_neuron --port=8500 --rest_api_port=8501 --model_name=${MODEL_NAME} --model_base_path=${MODEL_BASE_PATH}/${MODEL_NAME} "$@"' >> /usr/local/bin/entrypoint.sh \
 && chmod +x /usr/local/bin/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/license.txt -o /license.txt

COPY neuron-entrypoint.py /usr/local/bin/dockerd-entrypoint.py
COPY neuron-monitor.sh /usr/local/bin/neuron-monitor.sh

RUN chmod +x /usr/local/bin/dockerd-entrypoint.py \
 && chmod +x /usr/local/bin/neuron-monitor.sh

ENTRYPOINT ["python", "/usr/local/bin/dockerd-entrypoint.py"]
CMD ["/usr/local/bin/entrypoint.sh"]