It is highly recommended to use Docker.

But you can install Tensorflow Serving without using Docker as well.

You need to run the below mentioned commands in Linux Terminal.

You can install Tensorflow Serving using APT. Code for the same is shown below:

#if you already installed tensorflow-model-server, you should first uninstall it #using
apt-get remove tensorflow-model-server

#Add TensorFlow Serving distribution URI as a package source (one time setup)

echo "deb [arch=amd64] http://storage.googleapis.com/tensorflow-serving-apt stable tensorflow-model-server tensorflow-model-server-universal" | sudo tee /etc/apt/sources.list.d/tensorflow-serving.list && \
curl https://storage.googleapis.com/tensorflow-serving-apt/tensorflow-serving.release.pub.gpg | sudo apt-key add -

#Install and update TensorFlow ModelServer
apt-get update && apt-get install tensorflow-model-server

Once installed, the binary can be invoked using the command tensorflow_model_server.

You can upgrade to a newer version of tensorflow-model-server with:

apt-get upgrade tensorflow-model-server

For more information, refer the link, https://www.tensorflow.org/tfx/serving/setup#installing_using_apt

You can install TensorFlow serving without using a docker:

• Building from source

• TensorFlow Serving Python API PIP package

  pip install tensorflow-serving-api

You can install TensorFlow serving using any of the following 3 ways :

• Installing using Docker

• Building from source

• TensorFlow Serving Python API PIP package

  pip install tensorflow-serving-api

https://www.tensorflow.org/tfx/serving/setup#tensorflow_serving_python_api_pip_package

https://github.com/tensorflow/serving/blob/master/tensorflow_serving/g3doc/setup.md