[lmi] remove redundant auto logic from python handler #2152
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
lanking520
reviewed
Jul 10, 2024
| from djl_python.rolling_batch.scheduler_rolling_batch import SchedulerRollingBatch | ||
| return SchedulerRollingBatch | ||
| elif rolling_batch_type == "scheduler": | ||
| def get_rolling_batch_class_from_str(rolling_batch_type: str): |
There was a problem hiding this comment.
we should have deprecation warning or a fallback for auto. There are still some customer setting that to auto today.
There was a problem hiding this comment.
"auto" is still valid, but we just handle it here instead https://github.com/deepjavalibrary/djl-serving/blob/master/wlm/src/main/java/ai/djl/serving/wlm/LmiConfigRecommender.java#L81.
I don't think the logic here is ever invoked for "auto" in the current state.
lanking520
approved these changes
Jul 10, 2024
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Outdated suggestions cannot be applied.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.
Description
There is quite a bit of old/outdated logic scattered throughout djl_python and our default handlers. I'll be raising PRs to slowly clear out this outdated logic.
This change removes the "auto" logic for rolling batch from out python code. This logic has been fully moved to the LmiConfigRecommender on the java side. The logic here is not up to date anymore either.