Skip to content

Conversation

@prwhelan
Copy link
Member

We want to gate the inference endpoint cache behind a NodeFeature so that it will only enable if every node in the cluster can support it. This closes the risk that a master node can be an earlier version of the cache, potentially handling the ClearCache action without having the code for it.

Resolve #134809

We want to gate the inference endpoint cache behind a NodeFeature so
that it will only enable if every node in the cluster can support it.
This closes the risk that a master node can be an earlier version of the
cache, potentially handling the ClearCache action without having the
code for it.

Resolve elastic#134809
@prwhelan prwhelan added >non-issue :ml Machine learning Team:ML Meta label for the ML team v9.2.0 labels Sep 23, 2025
@prwhelan prwhelan marked this pull request as ready for review September 24, 2025 18:40
@elasticsearchmachine
Copy link
Collaborator

Pinging @elastic/ml-core (Team:ML)

@prwhelan prwhelan enabled auto-merge (squash) September 25, 2025 12:43
@prwhelan prwhelan merged commit 5aebcce into elastic:main Sep 25, 2025
34 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

:ml Machine learning >non-issue Team:ML Meta label for the ML team v9.2.0

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[ML] ClearInferenceEndpointCacheAction breaks rolling upragde tests

3 participants