fix: training never replaces cold-start model _drop_timestamp called as instance method - #81
Open
madhugoutham wants to merge 3 commits into
Open
fix: training never replaces cold-start model _drop_timestamp called as instance method#81madhugoutham wants to merge 3 commits into
madhugoutham wants to merge 3 commits into
Conversation
_drop_timestamp is a module-level function, not a method on LatencyPredictor. Calling it via self. raised AttributeError on every retrain attempt, silently caught, leaving the cold-start stub model permanently installed instead of a real trained one. Also drops the @staticmethod decorator on the module-level definition -- it has no effect outside a class and was misleading. Fixes llm-d#80 Signed-off-by: Madhu Goutham Reddy Ambati <mambati@redhat.com>
Signed-off-by: madhugoutham <79179882+madhugoutham@users.noreply.github.com> Signed-off-by: Madhu Goutham Reddy Ambati <mambati@redhat.com>
madhugoutham
marked this pull request as ready for review
August 18, 2026 02:28
Signed-off-by: Madhu Goutham Reddy Ambati <mambati@redhat.com>
Member
Author
|
PTAL @kaushikmitr |
|
This PR is marked as stale after 21d of inactivity. After an additional 14d of inactivity (7d to become rotten, then 7d more), it will be closed. To prevent this PR from being closed, add a comment or remove the |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Fixes the training failure caused by calling the module-level
_drop_timestamp()helper asself._drop_timestamp().The fix:
@staticmethoddecorator;_drop_timestamp()directly at all four call sites;Why is this change needed?
The previous code raised:
text
AttributeError:
LatencyPredictorobject has no attribute_drop_timestampThe exception was caught by the training loop, leaving the cold-start or previously loaded model installed instead of replacing it with a newly trained model.
How was this tested?
Fixes #80