phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

test: Bump slow_callback_duration to 200ms to avoid flaky remote vLLM unit tests (#1675)

Browse source 
# What does this PR do?

This avoids flaky timeout issue observed in CI builds, e.g.
3891286596

## Test Plan

Ran multiple times and pass consistently.

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-03-18 00:33:04 -04:00 • committed by GitHub
parent 2d2bb701fa
commit 0bdfc71f8d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/unit/providers/inference/test_remote_vllm.py
View file

@ -187,8 +187,8 @@ def test_chat_completion_doesnt_block_event_loop(caplog):
loop.set_debug(True) loop.set_debug(True)
caplog.set_level(logging.WARNING) caplog.set_level(logging.WARNING)
# Log when event loop is blocked for more than 100ms # Log when event loop is blocked for more than 200ms
loop.slow_callback_duration = 0.1 loop.slow_callback_duration = 0.2
# Sleep for 500ms in our delayed http response # Sleep for 500ms in our delayed http response
sleep_time = 0.5 sleep_time = 0.5