Make unigram cache optional#1763
Open
wangrunji0408 wants to merge 4 commits intohuggingface:mainfrom
Open
Conversation
Collaborator
ArthurZucker
left a comment
ArthurZucker
left a comment
There was a problem hiding this comment.
Sorry for my late review! happy to merge, can you also update the python bindings to expose this in python as well! Can come in handy!
Comment on lines
+605
to
610
| /// Get a mutable reference to the model | ||
| pub fn get_model_mut(&mut self) -> &mut M { | ||
| &mut self.model | ||
| } | ||
|
|
||
| /// Set the added vocabulary. |
Collaborator
There was a problem hiding this comment.
as this is unused here I would not put it in this PR!
Collaborator
ArthurZucker
left a comment
ArthurZucker
left a comment
There was a problem hiding this comment.
Ah actually I am not sure I understand the point here, you can just already resize to 0 should not make. a difference
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
We observed that the Unigram model's cache introduces significant contention overhead under multi-threaded scenarios. To mitigate this, we made the Unigram cache optional following BPE model's approach. Users can now disable it via
resize_cache(0). Additionally, we addedTokenizerImpl::get_model_mutto obtain a mutable reference of model.