Repository navigation
Conversation
AMOOOMA
marked this pull request as ready for review
October 21, 2026 21:25
Contributor
Author
|
R: @tvalentyn |
Contributor
|
Stopping reviewer notifications for this pull request: review requested by someone other than the bot, ceding control. If you'd like to restart, comment |
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #40714 +/- ##
========================================
Coverage 80.04% 80.05%
========================================
Files 490 490
Lines 82916 83031 +115
========================================
+ Hits 66373 66467 +94
- Misses 16543 16564 +21
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
tvalentyn
reviewed
Oct 21, 2026
| self.models = models | ||
| self.use_model_manager = not isinstance(models, list) | ||
| self.model_tag = model_tag | ||
| self.metric_tag = metric_tag or model_tag |
Contributor
There was a problem hiding this comment.
could we clarify in the docstring the difference between these two concepts?
…te; document model_tag vs metric_tag
…note that model updates should only change weights
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
When
RunInferenceupdates its model via side input (ModelMetadata),_RunInferenceDoFn._load_modelacquires the new model under the updatedmodel_idtag (self._cur_tag) soModelManagercaches and evicts the new model version separately from the previous version, while theBeamML_RunInferencetransform annotation remains fixed at construction time (self._model_tag/model_identifier).This PR passes
metric_tag=self._model_tagthrough_SharedModelWrappertoModelManager.acquire_model(..., metric_tag=...), and mapsmetric_tagto the active version tag inModelManagerandResourceEstimatorsonum_loaded_models_<metric_tag>andmemory_estimate_mb_<metric_tag>continue reporting under the originalmetric_tagacross runtime side-input model updates.Testing
test_run_inference_dofn_model_update_acquires_and_releases_matching_taginbase_test.pyto verifymetric_tagpreservation across model updates.test_model_manager_metrics_with_metric_taginmodel_manager_test.py.