update serve autoscaling docs #57652
Open
+289
−37
Conversation
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
Signed-off-by: abrar <[email protected]>
Signed-off-by: abrar <[email protected]>
Signed-off-by: abrar <[email protected]>
ray-gardener
bot
added
serve
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
This PR fixes critical documentation gaps and inaccuracies in Ray Serve autoscaling docs. Key additions include the previously undocumented
aggregation_functionparameter, 9 autoscaling environment variables, and a comprehensive "How autoscaling metrics work" section with diagrams explaining the 4-stage metrics pipeline. The PR also corrects therecord_autoscaling_stats()timeout value (10s not 30s), clarifies the two-stage downscaling behavior, and fixes themax_replicasdefault value explanation. Additionally, it adds deprecation notices for simple mode→aggregate mode and handle-based→replica-based metrics collection transitions.