Skip to content

Longer smoketest timeout #971

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
bkorycki merged 2 commits into from
Apr 10, 2025
Merged

Longer smoketest timeout #971

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7717df0
25 min timeout
bkorycki Apr 10, 2025
b25c2e4
lint
bkorycki Apr 10, 2025
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: 3 additions & 3 deletions plugins/validation_tests/test_object_creation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,6 @@
from modelgauge.sut_capabilities import AcceptsTextPrompt
from modelgauge.sut_registry import SUTS

from modelgauge.suts.huggingface_chat_completion import HUGGING_FACE_TIMEOUT
from modelgauge.test_registry import TESTS
from modelgauge.tests.safe_v1 import BaseSafeTestVersion1 # see "workaround" below
from modelgauge_tests.fake_secrets import fake_all_secrets
Expand All @@ -27,6 +26,7 @@
load_plugins()

_FAKE_SECRETS = fake_all_secrets()
TIMEOUT = 25 * 60 # 25 minutes. Baseten is the slowest to startup.


def ensure_public_dependencies(dependencies):
Expand Down Expand Up @@ -111,7 +111,7 @@ def test_all_suts_construct_and_record_init(sut_name):
# but still fails if the external service really is flaky or slow, so we can
# get a sense of a real user's experience.
@expensive_tests
@pytest.mark.timeout(HUGGING_FACE_TIMEOUT + 45) # Hugging Face spinup, plus some time for the test itself
@pytest.mark.timeout(TIMEOUT)
@pytest.mark.parametrize("sut_name", set(SUTS.keys()) - SUTS_THAT_WE_DONT_CARE_ABOUT_FAILING)
def test_all_suts_can_evaluate(sut_name):

Expand All @@ -131,7 +131,7 @@ def test_all_suts_can_evaluate(sut_name):


@expensive_tests
@pytest.mark.timeout(HUGGING_FACE_TIMEOUT + 45) # Hugging Face spinup, plus some time for the test itself
@pytest.mark.timeout(TIMEOUT)
@pytest.mark.parametrize("sut_name", set(SUTS.keys()) - SUTS_THAT_WE_DONT_CARE_ABOUT_FAILING)
def test_can_cache_all_sut_responses(sut_name, tmpdir):
sut = SUTS.make_instance(sut_name, secrets=load_secrets_from_config())
Expand Down