Developing with Docker

Pulling a development image

For a development environment where you can build TensorFlow Serving, you can try:

dockerpulltensorflow/serving:latest-devel

For a development environment where you can build TensorFlow Serving with GPU support, use:

dockerpulltensorflow/serving:latest-devel-gpu

See the Docker Hub tensorflow/serving repo for other versions of images you can pull.

Development example

After pulling one of the development Docker images, you can run it while opening the gRPC port (8500):

dockerrun-it-p8500:8500--gpusalltensorflow/serving:latest-devel

Testing the development environment

To test a model, from inside the container try:

# train the mnist model
pythontensorflow_serving/example/mnist_saved_model.py/tmp/mnist_model
# serve the model
tensorflow_model_server--port=8500--model_name=mnist--model_base_path=/tmp/mnist_model/&
# test the client
pythontensorflow_serving/example/mnist_client.py--num_tests=1000--server=localhost:8500

Dockerfiles

We currently maintain the following Dockerfiles:

• Dockerfile, which is a minimal VM with TensorFlow Serving installed.

• Dockerfile.gpu, which is a minimal VM with TensorFlow Serving with GPU support to be used with nvidia-docker.

• Dockerfile.devel, which is a minimal VM with all of the dependencies needed to build TensorFlow Serving.

• Dockerfile.devel-gpu, which is a minimal VM with all of the dependencies needed to build TensorFlow Serving with GPU support.

Building a container from a Dockerfile

If you'd like to build your own Docker image from a Dockerfile, you can do so by running the Docker build command:

Dockerfile:

dockerbuild--pull-t$USER/tensorflow-serving.

Dockerfile.gpu:

dockerbuild--pull-t$USER/tensorflow-serving-gpu-fDockerfile.gpu.

Dockerfile.devel:

dockerbuild--pull-t$USER/tensorflow-serving-devel-fDockerfile.devel.

Dockerfile.devel-gpu:

dockerbuild--pull-t$USER/tensorflow-serving-devel-gpu-fDockerfile.devel-gpu.

TIP: Before attempting to build an image, check the Docker Hub tensorflow/serving repo to make sure an image that meets your needs doesn't already exist.

Building from sources consumes a lot of RAM. If RAM is an issue on your system, you may limit RAM usage by specifying --local_ram_resources=2048 while invoking Bazel. See the Bazel docs for more information. You can use this same mechanism to tweak the optmizations you're building TensorFlow Serving with. For example:

dockerbuild--pull--build-argTF_SERVING_BUILD_OPTIONS="--copt=-mavx \
 --cxxopt=-D_GLIBCXX_USE_CXX11_ABI=0 --local_ram_resources=2048"-t\
$USER/tensorflow-serving-devel-fDockerfile.devel.

Running a container

This assumes you have built the Dockerfile.devel container.

To run the container opening the gRPC port (8500):

dockerrun-it-p8500:8500$USER/tensorflow-serving-devel

TIP: If you're running a GPU image, be sure to run using the NVIDIA runtime --runtime=nvidia.

From here, you can follow the instructions for testing a development environment.

Building an optimized serving binary

When running TensorFlow Serving's ModelServer, you may notice a log message that looks like this:

I external/org_tensorflow/tensorflow/core/platform/cpu_feature_guard.cc:141]
Your CPU supports instructions that this TensorFlow binary was not compiled to
use: AVX2 FMA

This indicates that your ModelServer binary isn't fully optimized for the CPU its running on. Depending on the model you are serving, further optimizations may not be necessary. However, building an optimized binary is straight-forward.

When building a Docker image from the provided Dockerfile.devel or Dockerfile.devel-gpu files, the ModelServer binary will be built with the flag -march=native. This will cause Bazel to build a ModelServer binary with all of the CPU optimizations the host you're building the Docker image on supports.

To create a serving image that's fully optimized for your host, simply:

1. Clone the TensorFlow Serving project

   gitclonehttps://github.com/tensorflow/serving
   cdserving
   

2. Build an image with an optimized ModelServer

   • For CPU:

     dockerbuild--pull-t$USER/tensorflow-serving-devel\
     -ftensorflow_serving/tools/docker/Dockerfile.devel.
     

   • For GPU: `

     dockerbuild--pull-t$USER/tensorflow-serving-devel-gpu\
     -ftensorflow_serving/tools/docker/Dockerfile.devel-gpu.
     

3. Build a serving image with the development image as a base

   • For CPU:

     dockerbuild-t$USER/tensorflow-serving\
     --build-argTF_SERVING_BUILD_IMAGE=$USER/tensorflow-serving-devel\
     -ftensorflow_serving/tools/docker/Dockerfile.
     

     Your new optimized Docker image is now $USER/tensorflow-serving, which you can use just as you would the standard tensorflow/serving:latest image.

   • For GPU:

     dockerbuild-t$USER/tensorflow-serving-gpu\
     --build-argTF_SERVING_BUILD_IMAGE=$USER/tensorflow-serving-devel-gpu\
     -ftensorflow_serving/tools/docker/Dockerfile.gpu.
     

     Your new optimized Docker image is now $USER/tensorflow-serving-gpu, which you can use just as you would the standard tensorflow/serving:latest-gpu image.