Skip to content

Fix multithreaded concurrency test to use shared tokenizer instance #1950

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ArthurZucker merged 1 commit into from
Feb 27, 2026
Merged

Fix multithreaded concurrency test to use shared tokenizer instance #1950

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions bindings/python/tests/bindings/test_tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -578,14 +578,15 @@ def test_multiprocessing_with_parallelism(self):
multiprocessing_with_parallelism(tokenizer, True)

def test_multithreaded_concurrency(self):
# Thread worker functions
# Create a single shared tokenizer instance (thread-safe)
shared_tokenizer = Tokenizer(BPE())

# Thread worker functions that use the SAME tokenizer instance
def encode_batch(batch):
tokenizer = Tokenizer(BPE())
return tokenizer.encode_batch(batch)
return shared_tokenizer.encode_batch(batch)

def encode_batch_fast(batch):
tokenizer = Tokenizer(BPE())
return tokenizer.encode_batch_fast(batch)
return shared_tokenizer.encode_batch_fast(batch)

# Create some significant workload
batches = [
Expand All @@ -594,7 +595,7 @@ def encode_batch_fast(batch):
["my name is ringo " * 50] * 20,
]

# Many encoding operations to run concurrently
# Many encoding operations to run concurrently using the same tokenizer
tasks = [
(encode_batch, batches[0]),
(encode_batch_fast, batches[1]),
Expand Down
Loading