Skip to content

Creating multiple InferenceModels with the same ModelName causes inconsistencies #394

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Tracked by #362
ahg-g opened this issue Feb 23, 2025 · 0 comments · Fixed by #393
Closed
Tracked by #362

Creating multiple InferenceModels with the same ModelName causes inconsistencies #394

ahg-g opened this issue Feb 23, 2025 · 0 comments · Fixed by #393
Labels
kind/bug Categorizes issue or PR as related to a bug.

Comments

@ahg-g
Copy link
Contributor

ahg-g commented Feb 23, 2025

Currently the logic tracks the models by Spec.ModelName, since this is not guaranteed to be unique within the cluster, we could run into two issues:

  1. If the model name changes on the same InferenceModel object, we don't delete the original model entry in the datastore.
  2. We don't enforce the semantics that the modelName with the oldest creation timestamp is retained. While the api is assuming that this is enforced by another controller via the Ready condition, we don't have this controller yet, and so currently the behavior is unpredictable depending on InferenceModel events order.

/kind bug

@k8s-ci-robot k8s-ci-robot added the kind/bug Categorizes issue or PR as related to a bug. label Feb 23, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
kind/bug Categorizes issue or PR as related to a bug.
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants