Are TF Serving minor versions always backwards compatible?

[law-lin]

Question

Is there a guarantee that TF Serving minor versions are always backwards compatible?

For example, if I have a model trained on TF 2.x, is there a guarantee that the model can run on any TF Serving 2.y where y >= x?

[singhniraj08]

@law-lin,

Underneath the hood, TensorFlow Serving uses the TensorFlow runtime to do the actual inference on your requests.
Referring to TensorFlow version compatibility, Code and data that worked with a previous minor release and which depends only on the non-experimental public API will continue to work unchanged.
To see what's covered in backward compatibility, refer here.
Thank you!

[github-actions]

This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.

[github-actions]

This issue was closed due to lack of activity after being marked stale for past 7 days.

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No