[CI] Update test markers and configurations to use 'full_model' for L4 nightly tests (#2641)

Signed-off-by: wangyu <410167048@qq.com>

tests/diffusion/models/glm_image/test_glm_image_sp.py

@@ -6,6 +6,8 @@ import pytest
 
 from vllm_omni.diffusion.data import DiffusionParallelConfig
 
+pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
+
 
 @pytest.fixture(scope="function", autouse=True)
 def setup_sp_groups(mocker):
@@ -24,9 +26,6 @@ def setup_sp_groups(mocker):
     yield
 
 
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
-
-
 def test_glm_image_sp_plan_defined():
     """Test that _sp_plan is properly defined on GlmImageTransformer2DModel."""
     from vllm_omni.diffusion.models.glm_image.glm_image_transformer import (