drop ascend scheduler (#4498)

Ascend scheduler was added for non chunk prefill case before, since that
the npu ops didn't work well with chunked prefill.

Now the ops with chunked prefill work better, it's time to remove the
ascend scheduler to use vLLM default scheduler.

- vLLM version: v0.11.2

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

tests/ut/quantization/test_w8a8_dynamic.py

@@ -33,13 +33,6 @@ class TestAscendW8A8FusedMoEMethod(TestBase):
             mock_get_ep_group.return_value = mock_ep_group
             mock_ascend_config = Mock()
 
-            # 创建一个具有具体属性的 Mock 对象来表示 ascend_scheduler_config
-            mock_ascend_scheduler_config = Mock()
-            mock_ascend_scheduler_config.enabled = False
-            mock_ascend_scheduler_config.max_num_batched_tokens = 1024
-            mock_ascend_scheduler_config.max_model_len = 2048
-            mock_ascend_config.ascend_scheduler_config = mock_ascend_scheduler_config
-
             mock_ascend_config.torchair_graph_config = Mock(enabled=False)
             mock_ascend_config.enable_chunked_prefill = False
             mock_get_ascend_config.return_value = mock_ascend_config