[CI/Build] Fix memory cleanup in MM test (#39411)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

.buildkite/test_areas/models_multimodal.yaml

@@ -56,7 +56,8 @@ steps:
   - tests/models/multimodal
   commands:
     - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
-    - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/processing
+    - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py  --ignore models/multimodal/generation/test_memory_leak.py --ignore models/multimodal/processing
+    - pytest models/multimodal/generation/test_memory_leak.py -m core_model
     - cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model  # Otherwise, mp_method="spawn" doesn't work
   mirror:
     amd:

tests/models/multimodal/generation/test_memory_leak.py

@@ -124,7 +124,7 @@ def llm(monkeypatch):
 
 @pytest.mark.core_model
 @pytest.mark.parametrize("image_urls", [TEST_IMAGE_NAMES], indirect=True)
-def test_qwen3_vl_no_memory_leak(llm, image_urls: list[str]) -> None:
+def test_no_memory_leak(llm, image_urls: list[str]) -> None:
     model_info = HF_EXAMPLE_MODELS.find_hf_info(MODEL_NAME)
     model_info.check_available_online(on_fail="skip")
     model_info.check_transformers_version(on_fail="skip")