[Serve] Fixing DeploymentStateManager qualifying replicas as running prematurely #43075
Conversation
This file contains 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
…g prematurely (ray-project#43025) Currently, DeploymentStateManager is qualifying replicas as running even thought they aren't actually running yet. This entails issues during downscaling: - DefaultDeploymentScheduler is supposed to prefer STARTING/STOPPING/etc replicas during downscaling for stopping - With replicas marked as replicas prematurely, DeploymentScheduler in some cases would pick actually running replicas for stopping even though there are still ones that aren't actually running yet --------- Signed-off-by: Alexey Kudinkin <[email protected]>
alexeykudinkin
approved these changes
Feb 9, 2024
zhe-thoughts
approved these changes
Feb 9, 2024
Signed-off-by: Edward Oakes <[email protected]>
…nto cp-alexey-fix
|
I believe the test failures are due to a transient issue with hugging face |
|
Indeed it was -- retry worked |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Why are these changes needed?
Cherry-picking #43025
Related issue number
Closes #43034
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/under thecorresponding
.rstfile.