Skip to content

Conversation

jonathan-buttner
Copy link
Contributor

This PRs refactors how the inference API threadpools are created to support returning multiple ScalingExecutorBuilder objects. This will let us return one for most utility threads and one that is used specifically for returning responses. That change is made in this PR: #133861

This PR renames the function to indicate that it will return multiple executors.

@jonathan-buttner jonathan-buttner added >non-issue :ml Machine learning Team:ML Meta label for the ML team v9.2.0 labels Sep 2, 2025

public static ScalingExecutorBuilder inferenceUtilityPool() {
return new ScalingExecutorBuilder(
public static ScalingExecutorBuilder[] inferenceUtilityExecutors() {
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Rename and return an array.

createThreadPool() signature is:

protected TestThreadPool createThreadPool(ExecutorBuilder<?>... executorBuilders) {

@jonathan-buttner jonathan-buttner marked this pull request as ready for review September 2, 2025 20:55
@elasticsearchmachine
Copy link
Collaborator

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

Copy link
Member

@davidkyle davidkyle left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@jonathan-buttner jonathan-buttner enabled auto-merge (squash) September 3, 2025 15:20
@jonathan-buttner jonathan-buttner merged commit c956b09 into elastic:main Sep 3, 2025
33 checks passed
@jonathan-buttner jonathan-buttner deleted the ml-inference-threadpool branch September 3, 2025 19:18
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.

3 participants