Add model caching for LabelScorer creation#222
Open
SimBe195 wants to merge 9 commits into
Open
Conversation
larissakl
approved these changes
May 19, 2026
curufinwe
approved these changes
May 26, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
For the
Encoderclass we have aEncoderModelCachewhich can be used to cache associated models (e.g. ONNX models for theOnnxEncoder) to avoid loading them multiple times when creating multiple instances. This PR adds a similar mechanism for LabelScorer creation. Since some LabelScorers use multiple models (e.g.StatefulOnnxLabelScorerwith the initializer-, updater- and scorer-model), the cache is keyed by the corresponding config selection. The cache class has been unified with theEncoderModelCacheinto a common class living insrc/Nn/LabelScorer/ModelCache.hh.