[TensorFlow][Inference][EC2] TensorFlow 2.18.0 Currency Release

dlc_developer_config.toml

@@ -37,10 +37,11 @@ deep_canary_mode = false
 [build]
 # Add in frameworks you would like to build. By default, builds are disabled unless you specify building an image.
 # available frameworks - ["autogluon", "huggingface_tensorflow", "huggingface_pytorch", "huggingface_tensorflow_trcomp", "huggingface_pytorch_trcomp", "pytorch_trcomp", "tensorflow", "pytorch", "stabilityai_pytorch"]
-build_frameworks = []
+build_frameworks = ["tensorflow"]
+
 
 # By default we build both training and inference containers. Set true/false values to determine which to build.
-build_training = true
+build_training = false
 build_inference = true
 
 # Set do_build to "false" to skip builds and test the latest image built by this PR
@@ -132,7 +133,7 @@ dlc-pr-tensorflow-2-habana-training = ""
 
 # Standard Framework Inference
 dlc-pr-pytorch-inference = ""
-dlc-pr-tensorflow-2-inference = ""
+dlc-pr-tensorflow-2-inference = "tensorflow/inference/buildspec-2-18-ec2.yml"
 dlc-pr-autogluon-inference = ""
 
 # Neuron Inference

tensorflow/inference/buildspec-2-18-ec2.yml

@@ -0,0 +1,72 @@
+account_id: &ACCOUNT_ID <set-$ACCOUNT_ID-in-environment>
+prod_account_id: &PROD_ACCOUNT_ID 763104351884
+region: &REGION <set-$REGION-in-environment>
+framework: &FRAMEWORK tensorflow
+version: &VERSION 2.18.0
+short_version: &SHORT_VERSION 2.18
+arch_type: x86
+# autopatch_build: "True"
+
+repository_info:
+  inference_repository: &INFERENCE_REPOSITORY
+    image_type: &INFERENCE_IMAGE_TYPE inference
+    root: !join [ *FRAMEWORK, "/", *INFERENCE_IMAGE_TYPE ]
+    repository_name: &REPOSITORY_NAME !join [pr, "-", *FRAMEWORK, "-", *INFERENCE_IMAGE_TYPE]
+    repository: &REPOSITORY !join [ *ACCOUNT_ID, .dkr.ecr., *REGION, .amazonaws.com/, *REPOSITORY_NAME ]
+    release_repository_name: &RELEASE_REPOSITORY_NAME !join [ *FRAMEWORK, "-", *INFERENCE_IMAGE_TYPE ]
+    release_repository: &RELEASE_REPOSITORY !join [ *PROD_ACCOUNT_ID, .dkr.ecr., *REGION, .amazonaws.com/,
+                                                    *RELEASE_REPOSITORY_NAME ]
+
+context:
+  inference_context: &INFERENCE_CONTEXT
+    sagemaker_package_name:
+      source: docker/build_artifacts/sagemaker
+      target: sagemaker
+    init:
+      source: docker/build_artifacts/__init__.py
+      target: __init__.py
+    dockerd-entrypoint:
+      source: docker/build_artifacts/dockerd-entrypoint.py
+      target: dockerd-entrypoint.py
+    deep_learning_container:
+      source: ../../src/deep_learning_container.py
+      target: deep_learning_container.py
+
+images:
+  BuildEC2TensorflowCPUInferencePy3DockerImage:
+    <<: *INFERENCE_REPOSITORY
+    build: &TENSORFLOW_CPU_INFERENCE_PY3 false
+    image_size_baseline: &IMAGE_SIZE_BASELINE 4899
+    framework_version: &FRAMEWORK_VERSION 2.18.0
+    device_type: &DEVICE_TYPE cpu
+    python_version: &DOCKER_PYTHON_VERSION py3
+    tag_python_version: &TAG_PYTHON_VERSION py310
+    os_version: &OS_VERSION ubuntu20.04
+    tag: !join [ *FRAMEWORK_VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
+    latest_release_tag: !join [ *FRAMEWORK_VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION,
+                                "-ec2" ]
+    docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
+    target: ec2
+    # build_tag_override: "beta:2.16.1-cpu-py310-ubuntu20.04-ec2"
+    context:
+      <<: *INFERENCE_CONTEXT
+  BuildEC2TensorflowGPUInferencePy3DockerImage:
+    <<: *INFERENCE_REPOSITORY
+    build: &TENSORFLOW_GPU_INFERENCE_PY3 false
+    image_size_baseline: &IMAGE_SIZE_BASELINE 13100
+    framework_version: &FRAMEWORK_VERSION 2.18.0
+    device_type: &DEVICE_TYPE gpu
+    python_version: &DOCKER_PYTHON_VERSION py3
+    tag_python_version: &TAG_PYTHON_VERSION py310
+    cuda_version: &CUDA_VERSION cu122
+    os_version: &OS_VERSION ubuntu20.04
+    tag: !join [ *FRAMEWORK_VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION,
+                 "-ec2" ]
+    latest_release_tag: !join [ *FRAMEWORK_VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION,
+                                "-", *OS_VERSION, "-ec2" ]
+    docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
+                         *DEVICE_TYPE ]
+    target: ec2
+    # build_tag_override: "beta:2.16.1-gpu-py310-cu122-ubuntu20.04-ec2"
+    context:
+      <<: *INFERENCE_CONTEXT

tensorflow/inference/buildspec.yml

@@ -1 +1 @@
-buildspec_pointer: buildspec-2-16-sm.yml
+buildspec_pointer: buildspec-2-18-ec2.yml

tensorflow/inference/docker/2.18/py3/Dockerfile.cpu

@@ -0,0 +1,206 @@
+########################################################
+#  _____ ____ ____    ___
+# | ____/ ___|___ \  |_ _|_ __ ___   __ _  __ _  ___
+# |  _|| |     __) |  | || '_ ` _ \ / _` |/ _` |/ _ \
+# | |__| |___ / __/   | || | | | | | (_| | (_| |  __/
+# |_____\____|_____| |___|_| |_| |_|\__,_|\__, |\___|
+#                                         |___/
+#  ____           _
+# |  _ \ ___  ___(_)_ __   ___
+# | |_) / _ \/ __| | '_ \ / _ \
+# |  _ <  __/ (__| | |_) |  __/
+# |_| \_\___|\___|_| .__/ \___|
+#                  |_|
+########################################################
+
+FROM ubuntu:20.04 AS base_image
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    LD_LIBRARY_PATH="${LD_LIBRARY_PATH}:/usr/local/lib"
+
+RUN apt-get update \
+ && apt-get upgrade -y \
+ && apt-get autoremove -y \
+ && apt-get clean \
+ && rm -rf /var/lib/apt/lists/*
+
+FROM base_image AS ec2
+
+LABEL maintainer="Amazon AI"
+LABEL dlc_major_version="1"
+
+ARG PYTHON=python3.10
+ARG PYTHON_PIP=python3-pip
+ARG PIP=pip3
+ARG PYTHON_VERSION=3.10.14
+ARG TFS_URL=https://framework-binaries.s3.us-west-2.amazonaws.com/tensorflow_serving/r2.18_aws/cpu/2025-01-15-19-48/tensorflow_model_server
+ARG TFS_SHORT_VERSION=2.18
+
+# ENV variable to be passed to SageMaker stage
+ENV PIP=${PIP}
+ENV PYTHON=${PYTHON}
+
+# See http://bugs.python.org/issue19846
+ENV LANG=C.UTF-8
+# Python won’t try to write .pyc or .pyo files on the import of source modules
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+ENV LD_LIBRARY_PATH='/usr/local/lib:$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
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update \
+ && apt-get -y install --no-install-recommends \
+    curl \
+    gnupg2 \
+    ca-certificates \
+    emacs \
+    git \
+    unzip \
+    wget \
+    vim \
+    libbz2-dev \
+    liblzma-dev \
+    libffi-dev \
+    build-essential \
+    zlib1g-dev \
+    openssl \
+    libssl1.1 \
+    libreadline-gplv2-dev \
+    libncursesw5-dev \
+    libssl-dev \
+    libsqlite3-dev \
+    tk-dev \
+    libgdbm-dev \
+    libc6-dev \
+ && apt-get clean \
+ && rm -rf /var/lib/apt/lists/*
+
+# Install python3.10
+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
+
+RUN ${PIP} install --no-cache-dir \
+    "awscli<2" \
+    boto3 \
+    "cython<3.0" \
+    gevent \
+    requests \
+    grpcio \
+    "protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3" \
+    packaging \
+# using --no-dependencies to avoid installing tensorflow binary
+ && ${PIP} install --no-dependencies --no-cache-dir \
+    tensorflow-serving-api=="2.18.0"
+
+# Some TF tools expect a "python" binary
+RUN ln -s $(which ${PYTHON}) /usr/local/bin/python \
+ && ln -s $(which ${PIP}) /usr/bin/pip
+
+
+RUN curl $TFS_URL -o /usr/bin/tensorflow_model_server \
+ && chmod 555 /usr/bin/tensorflow_model_server
+
+# Expose ports
+# gRPC and REST
+EXPOSE 8500 8501
+
+# Set where models should be stored in the container
+RUN mkdir -p ${MODEL_BASE_PATH}
+
+# Create a script that runs the model server so we can use environment variables
+# while also passing in arguments from the docker command line
+RUN echo '#!/bin/bash \n\n' > /usr/bin/tf_serving_entrypoint.sh \
+ && echo '/usr/bin/tensorflow_model_server --port=8500 --rest_api_port=8501 --model_name=${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 ${HOME_DIR}/oss_compliance*
+
+RUN curl https://aws-dlc-licenses.s3.amazonaws.com/tensorflow-${TFS_SHORT_VERSION}/license.txt -o /license.txt
+
+RUN rm -rf /tmp/*
+
+CMD ["/usr/bin/tf_serving_entrypoint.sh"]
+
+#################################################################
+#  ____                   __  __       _
+# / ___|  __ _  __ _  ___|  \/  | __ _| | _____ _ __
+# \___ \ / _` |/ _` |/ _ \ |\/| |/ _` | |/ / _ \ '__|
+#  ___) | (_| | (_| |  __/ |  | | (_| |   <  __/ |
+# |____/ \__,_|\__, |\___|_|  |_|\__,_|_|\_\___|_|
+#              |___/
+#  ___                              ____           _
+# |_ _|_ __ ___   __ _  __ _  ___  |  _ \ ___  ___(_)_ __   ___
+#  | || '_ ` _ \ / _` |/ _` |/ _ \ | |_) / _ \/ __| | '_ \ / _ \
+#  | || | | | | | (_| | (_| |  __/ |  _ <  __/ (__| | |_) |  __/
+# |___|_| |_| |_|\__,_|\__, |\___| |_| \_\___|\___|_| .__/ \___|
+#                      |___/                        |_|
+#################################################################
+
+FROM ec2 AS sagemaker
+
+LABEL maintainer="Amazon AI"
+LABEL dlc_major_version="1"
+
+# Specify accept-bind-to-port 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
+LABEL com.amazonaws.sagemaker.capabilities.multi-models=true
+
+ARG TFS_SHORT_VERSION=2.18
+ENV SAGEMAKER_TFS_VERSION="${TFS_SHORT_VERSION}"
+ENV PATH="$PATH:/sagemaker"
+
+# nginx + njs
+RUN 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 \
+    nginx-module-njs \
+ && apt-get clean \
+ && rm -rf /var/lib/apt/lists/*
+
+# the Pins are for the TFS SageMaker Toolkit
+RUN ${PIP} install --no-cache-dir \
+    falcon==3.1.0 \
+    "gunicorn>=22.0.0"
+
+COPY ./sagemaker /sagemaker
+
+# Expose ports
+# gRPC and REST
+EXPOSE 8500 8501
+
+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 rm -rf /tmp/*
+
+CMD ["/usr/bin/tf_serving_entrypoint.sh"]