Skip to content

[Quantization] Skip Fp4 Test for compressed-tensors #19217

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 1 commit into from
Jun 5, 2025
Merged

[Quantization] Skip Fp4 Test for compressed-tensors #19217

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
1 change: 1 addition & 0 deletions tests/quantization/test_compressed_tensors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -651,6 +651,7 @@ def check_model(model):
assert output


@pytest.mark.skip(reason="Skip until the model config is updated")
Copy link
Contributor

Choose a reason for hiding this comment

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

medium

The reason for skipping the test is clear at a high level, but could you make it more specific for future maintainability? For example, mentioning which model config or linking to a tracking issue (e.g., a GitHub issue or JIRA ticket) would help in remembering to re-enable this test once the underlying issue is resolved. This would make it easier for someone else (or your future self) to understand the context and when to remove the skip.

Suggested change
@pytest.mark.skip(reason="Skip until the model config is updated")
@pytest.mark.skip(reason="Skip until 'nm-testing/TinyLlama-1.1B-Chat-v1.0-FP4' model config is updated for compatibility with the current compressed-tensors version. See issue #XYZ.")

def test_compressed_tensors_nvfp4a16(vllm_runner):
# run weight only example
model = "nm-testing/TinyLlama-1.1B-Chat-v1.0-FP4"
Expand Down