A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 5, 09:45 UTC
[CI/Build] Fix memory cleanup in MM test (#39411)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Apr 9, 2026 at 23:50 UTC
3b1d9c3156d22181fb99980eb2550772c854a2c2
2 files changed
+3
-2
.buildkite/test_areas/models_multimodal.yaml
+2
-1
@@ -56,7 +56,8 @@ steps:
56
- tests/models/multimodal
57
commands:
58
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
59
- - 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
59
+ - 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
60
+ - pytest models/multimodal/generation/test_memory_leak.py -m core_model
61
- 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
62
mirror:
63
amd:
tests/models/multimodal/generation/test_memory_leak.py
+1
-1
@@ -124,7 +124,7 @@ def llm(monkeypatch):
124
125
@pytest.mark.core_model
126
@pytest.mark.parametrize("image_urls", [TEST_IMAGE_NAMES], indirect=True)
127
-def test_qwen3_vl_no_memory_leak(llm, image_urls: list[str]) -> None:
127
+def test_no_memory_leak(llm, image_urls: list[str]) -> None:
128
model_info = HF_EXAMPLE_MODELS.find_hf_info(MODEL_NAME)
129
model_info.check_available_online(on_fail="skip")
130
model_info.check_transformers_version(on_fail="skip")