anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Bugfix] Apply function module marker per-model instead of hardcoding diffusion (#5875)

Browse Source 
Signed-off-by: khairulkabir1661 <khairulkabir1661@users.noreply.github.com>
Co-authored-by: khairulkabir1661 <khairulkabir1661@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Khairul Kabirkhairulkabir1661Claude Opus 4.6
 authored and GitHub committed 2026-09-25 14:17:19 -06:00
1 parent a8576ccb72
commit 5e36b5a86b
5 files changed
+50 -7
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/model_tests/diffusion/test_common_online.py
+2 -2
View File
@@ -31,8 +31,8 @@ from tests.model_tests.diffusion.task_runners import (
)
from vllm_omni.diffusion.model_metadata import get_diffusion_model_metadata
# NOTE : Hardware marks are added dynamically based on test requirements
pytestmark = [pytest.mark.diffusion, pytest.mark.xdist]
# NOTE: Hardware and model type marks are added dynamically based on test requirements and model type
pytestmark = [pytest.mark.xdist]
@pytest.fixture(autouse=True)