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/ut/ops/test_vocab_parallel_embedding.py

@@ -209,7 +209,12 @@ class TestAscendLogitsProcessor(unittest.TestCase):
                 return_value=torch.randn(1, self.vocab_size)),
             patch(
                 "vllm_ascend.ops.vocab_parallel_embedding.get_lmhead_tp_group.all_gather",
-                return_value=torch.randn(1, self.vocab_size))
+                return_value=torch.randn(1, self.vocab_size)),
+            patch(
+                "vllm_ascend.core.schedule_config.AscendSchedulerConfig.initialize_from_config",
+                return_value=MagicMock(max_num_batched_tokens=1000,
+                                       max_model_len=512,
+                                       enable_chunked_prefill=False))
         ]
 
         for p in self.patches: