Revert "drop ascend scheduler" (#4580)

Reverts vllm-project/vllm-ascend#4498
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

tests/e2e/singlecard/test_vlm.py

@@ -20,6 +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
@@ -54,6 +55,40 @@ 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")
+    img_questions = [
+        "What is the content of this image?",
+        "Describe the content of this image in detail.",
+        "What's in the image?",
+        "Where is this image taken?",
+    ]
+    images = [image] * len(img_questions)
+    prompts = prompt_template(img_questions)
+    with VllmRunner("Qwen/Qwen2.5-VL-3B-Instruct",
+                    max_model_len=4096,
+                    additional_config={
+                        'ascend_scheduler_config': {
+                            'enabled': True,
+                        },
+                    },
+                    mm_processor_kwargs={
+                        "min_pixels": 28 * 28,
+                        "max_pixels": 1280 * 28 * 28,
+                        "fps": 1,
+                    },
+                    enforce_eager=True) as vllm_model:
+        outputs = vllm_model.generate_greedy(prompts=prompts,
+                                             images=images,
+                                             max_tokens=64)
+        assert len(outputs) == len(prompts)
+        for _, output_str in outputs:
+            assert output_str, "Generated output should not be empty."
+
+
 def test_multimodal_audio():
     audio_prompt = "".join([
         f"Audio {idx+1}: <|audio_bos|><|AUDIO|><|audio_eos|>\n"