Skip to content

increase timing, fix flaky failures #124

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
Qubitium merged 1 commit into from
Apr 27, 2026
Merged

increase timing, fix flaky failures #124

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
6 changes: 4 additions & 2 deletions tests/test_openai_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,7 +273,9 @@ def test_openai_compatible_server_waits_for_missing_earlier_generation_order() -
session=backend,
model_name="fake-model",
max_batch_size=2,
batch_window_s=0.05,
# Keep a wider window so slow CI schedulers still observe the delayed earlier
# request within the same first refill stream.
batch_window_s=0.2,
) as server:
batcher = server._generate_batcher
assert batcher is not None
Expand All @@ -294,7 +296,7 @@ def submit(prompt: str, order_index: int, *, delay_s: float = 0.0) -> str:
futures = [
executor.submit(submit, "one", 1),
executor.submit(submit, "two", 2),
executor.submit(submit, "zero", 0, delay_s=0.01),
executor.submit(submit, "zero", 0, delay_s=0.02),
]
outputs = [future.result() for future in futures]

Expand Down