Drop ascend scheduler (#4623)

It's safe to drop ascend scheduler now. The related test and doc has
been removed already


- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

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

tests/ut/ops/test_linear.py

@@ -99,7 +99,7 @@ class TestAscendRowParallelLinear(BaseLinearTest):
 
         ascend_config._ASCEND_CONFIG = MagicMock()
         ascend_config._ASCEND_CONFIG.oproj_tensor_parallel_size = 2
-        ascend_config._ASCEND_CONFIG.ascend_scheduler_config.enabled = False
+        ascend_config._ASCEND_CONFIG.recompute_scheduler_enable = False
 
         linear = AscendRowParallelLinear(
             input_size=16,

tests/ut/ops/test_vocab_parallel_embedding.py

@@ -209,12 +209,7 @@ 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)),
-            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))
+                return_value=torch.randn(1, self.vocab_size))
         ]
 
         for p in self.patches:

tests/ut/test_platform.py

@@ -32,7 +32,6 @@ class TestNPUPlatform(TestBase):
     def mock_vllm_ascend_config():
         mock_ascend_config = MagicMock()
         mock_ascend_config.torchair_graph_config.enabled = False
-        mock_ascend_config.ascend_scheduler_config.enabled = False
         mock_ascend_config.enable_shared_expert_dp = False
         return mock_ascend_config