[BugFix] Comment out newly added vlm e2e. (#3736)

This PR comments out newly added vlm e2e test of ascend scheduler
scenario because I found that when running in multi-batch this will
stuck. Need to add this back after dealing with this issue.
- vLLM version: v0.11.0rc3
- vLLM main:
https://github.com/vllm-project/vllm/commit/17c540a993af88204ad1b78345c8a865cf58ce44

Signed-off-by: whx-sjtu <2952154980@qq.com>
This commit is contained in:
whx authored and GitHub committed 2025-10-25 10:34:59 +08:00
1 parent 9e150e5009
commit d5609e2c48
1 file changed
+3 -1
+3 -1
View File
@@ -20,7 +20,7 @@
Run `pytest tests/test_offline_inference.py`.
"""
import pytest
from vllm import SamplingParams
from vllm.assets.audio import AudioAsset
from vllm.assets.image import ImageAsset
@@ -55,6 +55,8 @@ def test_multimodal_vl(prompt_template):
assert output_str, "Generated output should not be empty."
@pytest.mark.skip(reason="This e2e test will stuck in multi-batch scenario. "
"Add this back after fixing the issue.")
def test_multimodal_ascend_scheduler(prompt_template):
image = ImageAsset("cherry_blossom") \
.pil_image.convert("RGB")