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>