Fix multithreaded concurrency test to use shared tokenizer instance#1950
Open
mrkm4ntr wants to merge 1 commit intohuggingface:mainfrom
Open
Fix multithreaded concurrency test to use shared tokenizer instance#1950mrkm4ntr wants to merge 1 commit intohuggingface:mainfrom
mrkm4ntr wants to merge 1 commit intohuggingface:mainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR fixes the
test_multithreaded_concurrencytest to properly verify thread safety by using a sharedtokenizer instance across multiple threads, rather than creating separate instances per thread.
Problem
The existing test in commit
6eba494a(#1864) was designed to test thread safety, but it created a newTokenizer(BPE())instance within each worker function. This meant each thread was using its own tokenizer,which doesn't test the actual scenario where multiple threads access the same tokenizer instance.