Adding gunicorn config file.

[samueleresca]

Description of changes:

This change provides a better way to configure gunicorn in the serving container.

Instead of using ad-hoc env vars (see SAGEMAKER_GUNICORN_WORKERS or SAGEMAKER_GUNICORN_THREADS) we can use the configuration file approach (https://docs.gunicorn.org/en/stable/settings.html#config-file).

In this way, it is possible to specify the configuration of gunicorn along with code of the model:

    model1
        |--[model_version_number]
            |--variables
            |--saved_model.pb
    model2
        |--[model_version_number]
            |--assets
            |--variables
            |--saved_model.pb
    code
        |--lib
            |--external_module
        |--inference.py
        |--gunicorn_config.py

The resulting gunicorn_command should look like something similar to this:

gunicorn -c /opt/ml/model/code/gunicorn_config.py [<additional_arg>,...] python_service:app

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

[sagemaker-bot]

AWS CodeBuild CI Report

• CodeBuild project: sagemaker-tensorflow-serving-container-pr
• Commit ID: 5ebafa9a8cdc4f49390561390cc7dd3bbd6d6475
• Result: FAILED
• Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

[sagemaker-bot]

AWS CodeBuild CI Report

• CodeBuild project: sagemaker-tensorflow-serving-container-pr
• Commit ID: 5765e26a293730143510c0aab8532a12c1f90b8d
• Result: FAILED
• Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

[sagemaker-bot]

AWS CodeBuild CI Report

• CodeBuild project: sagemaker-tensorflow-serving-container-pr
• Commit ID: 158f1e7e6cceff32007a32092d6151667e01cd95
• Result: SUCCEEDED
• Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository