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 11, 08:45 UTC
[CI/Build] Skip broken ViT backend functionality test tempoarily (#30782)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Isotr0py committed
Dec 16, 2025 at 22:45 UTC
4de08ad698674560be7abebd9437d698d1216872
1 file changed
+1
tests/models/multimodal/generation/test_vit_backend_functionality.py
+1
@@ -388,6 +388,7 @@ def run_video_test(config, mm_encoder_attn_backend, video_assets, vllm_runner):
388
"mm_encoder_attn_backend",
389
[None] + current_platform.get_supported_vit_attn_backends(),
390
)
391
+@pytest.mark.skip(reason="Broken test due to memory segmentation fault")
392
@create_new_process_for_each_test()
393
def test_vit_backend_functionality(
394
model_key: str,