[CI] Remove VLLM_TEST_CLEAN_GPU_MEMORY to avoid environment variable pollution that causes unnecessary GPU detection, thereby slowing down test case execution. (#3446)

Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: [Your Name] <your.email@example.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

tests/examples/offline_inference/test_internvla_a1.py

@@ -16,9 +16,9 @@ import pytest
 
 from tests.helpers.mark import hardware_test
 
-os.environ["VLLM_TEST_CLEAN_GPU_MEMORY"] = "1"
-
 REPO_ROOT = Path(__file__).resolve().parents[3]
+
+
 EXAMPLE_SCRIPT = REPO_ROOT / "examples" / "offline_inference" / "internvla_a1" / "end2end.py"
 
 
@@ -33,6 +33,7 @@ def _required_env(name: str) -> str:
 @pytest.mark.advanced_model
 @pytest.mark.diffusion
 @hardware_test(res={"cuda": "H100", "rocm": "MI325"})
+@pytest.mark.usefixtures("clean_gpu_memory_between_tests")
 def test_internvla_a1_offline_open_loop(run_level: str) -> None:
     if run_level != "advanced_model":
         pytest.skip("InternVLA-A1 offline evaluation requires real local checkpoints and dataset.")

tests/examples/offline_inference/test_text_to_image.py

@@ -11,7 +11,12 @@ from tests.examples.helpers import EXAMPLES, ExampleRunner, ReadmeSnippet
 from tests.helpers.assertions import assert_image_valid
 from tests.helpers.mark import hardware_marks
 
-pytestmark = [pytest.mark.full_model, pytest.mark.example, *hardware_marks(res={"cuda": "H100"})]
+pytestmark = [
+    pytest.mark.usefixtures("clean_gpu_memory_between_tests"),
+    pytest.mark.full_model,
+    pytest.mark.example,
+    *hardware_marks(res={"cuda": "H100"}),
+]
 
 T2I_SCRIPT = EXAMPLES / "offline_inference" / "text_to_image" / "text_to_image.py"
 README_PATH = T2I_SCRIPT.with_name("README.md")