Scale Triton from zero replicas on RepositoryIndex - #85
Merged
Conversation
… until server is up and ready before replying
… until server is up and ready before replying
…ing/SuperSONIC into scale-from-zero
…esh other parameters/comments and update probe defaults
Co-authored-by: Cursor <cursoragent@cursor.com>
…y CD reconciliation)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…ueued wakes Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Collaborator
Author
|
Ran Claude code review until it stopped returning new findings. Ready to merge. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
When Triton is at 0 replicas, a
RepositoryIndexrequest scales it tomax(1, keda.minReplicaCount)replicas. Envoy returns the index only after it has a healthy Triton upstream; otherwise the index is rejected.KEDA continues to handle scaling above the wake target and scaling back down. After
holdMinReplicasSecondswith no new index,minReplicaCountis restored to the configured idle value. Helm omitsspec.replicason the Triton Deployment so it does not override KEDA.Requires
keda.enabled: trueandenvoy.enabled: true. Setkeda.minReplicaCount: 0to release all replicas when idle. The Geddes CMS example values enable this.New values
scaleFromZero.enabledfalseRepositoryIndexscaleFromZero.readyTimeoutSeconds300RepositoryIndexscaleFromZero.holdMinReplicasSeconds300minReplicaCountat the wake target after the lastRepositoryIndexscaleFromZero.admissionImagepython:3.11-slimkeda.pollingInterval30keda.cooldownPeriod120minReplicaCount