Skip to content

[Fix] Fix gemma CI test failing on main #20124

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
merged 2 commits into from
Jun 27, 2025
Merged

[Fix] Fix gemma CI test failing on main #20124

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
94f6842
Fix gemma test
tdoublep Jun 26, 2025
7efba28
Handle gemma-3-4b-it correctly
tdoublep Jun 26, 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
25 changes: 14 additions & 11 deletions tests/models/language/generation/test_gemma.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,14 +7,17 @@


@pytest.mark.parametrize("model", MODELS)
def test_dummy_loader(vllm_runner, model: str) -> None:
with vllm_runner(
model,
load_format="dummy",
) as llm:
normalizers = llm.collective_rpc(lambda self: self.worker.model_runner.
model.model.normalizer.cpu().item())
assert np.allclose(
normalizers,
llm.llm_engine.model_config.hf_config.hidden_size**0.5,
rtol=1e-3)
def test_dummy_loader(vllm_runner, monkeypatch, model: str) -> None:
with monkeypatch.context() as m:
m.setenv("VLLM_ALLOW_INSECURE_SERIALIZATION", "1")
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

wondering why this cause failure?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it's because you're passing a function into collective_rpc which can only be serialized via pickle (insecure)

with vllm_runner(
model,
load_format="dummy",
) as llm:
normalizers = llm.model.collective_rpc(
lambda self: self.model_runner.model.model.normalizer.cpu(
).item())
assert np.allclose(
normalizers,
llm.model.llm_engine.model_config.hf_config.hidden_size**0.5,
rtol=1e-3)