使用 GPU 執行管道

ARG BASE=tensorflow/tensorflow:2.5.0-gpu
FROM $BASE

# Check that the chosen base image provides the expected version of Python interpreter.
ARG PY_VERSION=3.6
RUN [[ $PY_VERSION == `python -c 'import sys; print("%s.%s" % sys.version_info[0:2])'` ]] \
   || { echo "Could not find Python interpreter or Python version is different from ${PY_VERSION}"; exit 1; }

RUN pip install --upgrade pip \
    && pip install --no-cache-dir apache-beam[gcp]==2.29.0 \
    # Verify that there are no conflicting dependencies.
    && pip check

# Copy the Apache Beam worker dependencies from the Beam Python 3.6 SDK image.
COPY --from=apache/beam_python3.6_sdk:2.29.0 /opt/apache/beam /opt/apache/beam

# Apache Beam worker expects pip at /usr/local/bin/pip by default.
# Some images have pip in a different location. If necessary, make a symlink.
# This line can be omitted in Beam 2.30.0 and later versions.
RUN [[ `which pip` == "/usr/local/bin/pip" ]] || ln -s `which pip` /usr/local/bin/pip

# Set the entrypoint to Apache Beam SDK worker launcher.
ENTRYPOINT [ "/opt/apache/beam/boot" ]

# Select an NVIDIA base image with needed GPU stack from https://ngc.nvidia.com/catalog/containers/nvidia:cuda

FROM nvidia/cuda:11.0.3-cudnn8-runtime-ubuntu20.04

RUN \
    # Add Deadsnakes repository that has a variety of Python packages for Ubuntu.
    # See: https://launchpad.net/~deadsnakes/+archive/ubuntu/ppa
    apt-key adv --keyserver keyserver.ubuntu.com --recv-keys F23C5A6CF475977595C89F51BA6932366A755776 \
    && echo "deb http://ppa.launchpad.net/deadsnakes/ppa/ubuntu focal main" >> /etc/apt/sources.list.d/custom.list \
    && echo "deb-src http://ppa.launchpad.net/deadsnakes/ppa/ubuntu focal main" >> /etc/apt/sources.list.d/custom.list \
    && apt-get update \
    && apt-get install -y curl \
        python3.8 \
        # With python3.8 package, distutils need to be installed separately.
        python3-distutils \
    && rm -rf /var/lib/apt/lists/* \
    && update-alternatives --install /usr/bin/python python /usr/bin/python3.8 10 \
    && curl https://bootstrap.pypa.io/get-pip.py | python \
    && pip install --upgrade pip \
    # Install Apache Beam and Python packages that will interact with GPUs.
    && pip install --no-cache-dir apache-beam[gcp]==2.29.0 tensorflow==2.4.0 \
    # Verify that there are no conflicting dependencies.
    && pip check

# Copy the Apache Beam worker dependencies from the Beam Python 3.8 SDK image.
COPY --from=apache/beam_python3.8_sdk:2.29.0 /opt/apache/beam /opt/apache/beam

# Set the entrypoint to Apache Beam SDK worker launcher.
ENTRYPOINT [ "/opt/apache/beam/boot" ]

FROM nvidia/cuda:11.0.3-cudnn8-runtime-ubuntu20.04

# The Python version of the Dockerfile must match the Python version you use
# to launch the Dataflow job.

ARG PYTHON_VERSION=3.8

# Update PATH so we find our new Conda and Python installations.
ENV PATH=/opt/python/bin:/opt/conda/bin:$PATH

RUN apt-get update \
    && apt-get install -y wget \
    && rm -rf /var/lib/apt/lists/* \
    # The NVIDIA image doesn't come with Python pre-installed.
    # We use Miniconda to install the Python version of our choice.
    && wget -q https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \
    && bash Miniconda3-latest-Linux-x86_64.sh -b -p /opt/conda \
    && rm Miniconda3-latest-Linux-x86_64.sh \
    # Create a new Python environment with needed version, and install pip.
    && conda create -y -p /opt/python python=$PYTHON_VERSION pip \
    # Remove unused Conda packages, install necessary Python packages via pip
    # to avoid mixing packages from pip and Conda.
    && conda clean -y --all --force-pkgs-dirs \
    && pip install --upgrade pip \
    # Install Apache Beam and Python packages that will interact with GPUs.
    && pip install --no-cache-dir apache-beam[gcp]==2.29.0 tensorflow==2.4.0 \
    # Verify that there are no conflicting dependencies.
    && pip check \
    # Apache Beam worker expects pip at /usr/local/bin/pip by default.
    # You can omit this line when using Beam 2.30.0 and later versions.
    && ln -s $(which pip) /usr/local/bin/pip

# Copy the Apache Beam worker dependencies from the Apache Beam SDK for Python 3.8 image.
COPY --from=apache/beam_python3.8_sdk:2.29.0 /opt/apache/beam /opt/apache/beam

# Set the entrypoint to Apache Beam SDK worker launcher.
ENTRYPOINT [ "/opt/apache/beam/boot" ]

FROM apache/beam_python3.7_sdk:2.24.0
ENV INSTALLER_DIR="/tmp/installer_dir"

# The base image has TensorFlow 2.2.0, which requires CUDA 10.1 and cuDNN 7.6.
# You can download cuDNN from NVIDIA website
# https://developer.nvidia.com/cudnn
COPY cudnn-10.1-linux-x64-v7.6.0.64.tgz $INSTALLER_DIR/cudnn.tgz
RUN \
    # Download CUDA toolkit.
    wget -q -O $INSTALLER_DIR/cuda.run https://developer.download.nvidia.com/compute/cuda/10.1/Prod/local_installers/cuda_10.1.243_418.87.00_linux.run && \

    # Install CUDA toolkit. Print logs upon failure.
    sh $INSTALLER_DIR/cuda.run --toolkit --silent || (egrep '^\[ERROR\]' /var/log/cuda-installer.log && exit 1) && \
    # Install cuDNN.
    mkdir $INSTALLER_DIR/cudnn && \
    tar xvfz $INSTALLER_DIR/cudnn.tgz -C $INSTALLER_DIR/cudnn && \

    cp $INSTALLER_DIR/cudnn/cuda/include/cudnn*.h /usr/local/cuda/include && \
    cp $INSTALLER_DIR/cudnn/cuda/lib64/libcudnn* /usr/local/cuda/lib64 && \
    chmod a+r /usr/local/cuda/include/cudnn*.h /usr/local/cuda/lib64/libcudnn* && \
    rm -rf $INSTALLER_DIR

# A volume with GPU drivers will be mounted at runtime at /usr/local/nvidia.
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/nvidia/lib64:/usr/local/cuda/lib64

['worker_accelerator=type:nvidia-tesla-t4;count:1;install-nvidia-driver', ...]