aws / sagemaker-inference-toolkit

Serve machine learning models within a 🐳 Docker container using 🧠 Amazon SageMaker.
Apache License 2.0
385 stars 82 forks source link

Add support for SAGEMAKER_MODEL_SERVER_TIMEOUT_SECONDS variable #129

Closed davidthomas426 closed 1 year ago

davidthomas426 commented 1 year ago

Issue #, if available:

Description of changes: This provides a way for the customer to provide a timeout value specifically in seconds. This is needed due to a bug in multi-model-server that interpreted the existing timeout value in minutes even though it was documented to be in seconds.

We introduced a new variable rather than changing the meaning of the old variable out of concerns around backward-compatibility. We can revisit this later if needed.

Testing done:

Unit tests all passed.

Installed modified versions of MMS and this toolkit in a container and ran an end-to-end example to trigger the timeout to verify it works. It does :)

Merge Checklist

Put an x in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.

General

Tests

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

sagemaker-bot commented 1 year ago

AWS CodeBuild CI Report

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