[CI] Drop ascend scheduler from test

.github/workflows/_e2e_test.yaml

@@ -91,7 +91,6 @@ jobs:
           pytest -sv tests/e2e/singlecard/test_completion_with_prompt_embeds.py
           pytest -sv tests/e2e/singlecard/test_aclgraph.py
           pytest -sv tests/e2e/singlecard/test_aclgraph_mem.py
-          pytest -sv tests/e2e/singlecard/test_ascend_scheduler.py
           pytest -sv tests/e2e/singlecard/test_bge_model.py
           pytest -sv tests/e2e/singlecard/test_camem.py
           pytest -sv tests/e2e/singlecard/test_embedding.py

tests/ut/quantization/test_w8a8_dynamic.py

@@ -33,13 +33,6 @@ def setUp(self, mock_get_ep_group, mock_get_ascend_config,
             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

tests/ut/test_ascend_config.py

@@ -56,9 +56,6 @@ def test_init_ascend_config_without_additional_config(self):
         self.assertTrue(torchair_graph_config.enable_frozen_parameter)
         self.assertFalse(torchair_graph_config.enable_kv_nz)
 
-        ascend_scheduler_config = ascend_config.ascend_scheduler_config
-        self.assertFalse(ascend_scheduler_config.enabled)
-
     @_clean_up_ascend_config
     def test_init_ascend_config_with_additional_config(self):
         test_vllm_config = VllmConfig()
@@ -74,9 +71,6 @@ def test_init_ascend_config_with_additional_config(self):
                 "enable_kv_nz": True
             },
             "multistream_overlap_shared_expert": True,
-            "ascend_scheduler_config": {
-                "enabled": True
-            },
             "expert_map_path": "test_expert_map_path",
             "refresh": True,
         }
@@ -94,9 +88,6 @@ def test_init_ascend_config_with_additional_config(self):
         self.assertTrue(torchair_graph_config.enable_frozen_parameter)
         self.assertTrue(torchair_graph_config.enable_kv_nz)
 
-        ascend_scheduler_config = ascend_config.ascend_scheduler_config
-        self.assertTrue(ascend_scheduler_config.enabled)
-
     @_clean_up_ascend_config
     def test_init_ascend_config_with_refresh(self):
         test_vllm_config = VllmConfig()

tests/ut/test_platform.py

@@ -522,31 +522,6 @@ def test_check_and_update_config_310p_no_custom_ops(
         self.platform.check_and_update_config(vllm_config)
         self.assertEqual(vllm_config.compilation_config.custom_ops, [])
 
-    @patch('vllm_ascend.utils.get_ascend_device_type',
-           return_value=AscendDeviceType._910_93)
-    @patch("vllm_ascend.ascend_config.check_ascend_config")
-    @patch("vllm_ascend.ascend_config.init_ascend_config")
-    @patch(
-        "vllm_ascend.core.recompute_schedule_config.RecomputeSchedulerConfig.initialize_from_config"
-    )
-    def test_check_and_update_config_ascend_scheduler_config(
-            self, mock_init_recompute, mock_init_ascend, mock_check_ascend,
-            mock_soc_version):
-        mock_ascend_config = TestNPUPlatform.mock_vllm_ascend_config()
-        mock_ascend_config.ascend_scheduler_config.enabled = True
-        mock_init_ascend.return_value = mock_ascend_config
-        vllm_config = TestNPUPlatform.mock_vllm_config()
-        vllm_config.parallel_config.tensor_parallel_size = 1
-        mock_init_recompute.return_value = MagicMock()
-
-        with patch("vllm_ascend.core.schedule_config.AscendSchedulerConfig"
-                   ) as mock_scheduler:
-            from vllm_ascend import platform
-
-            importlib.reload(platform)
-            self.platform.check_and_update_config(vllm_config)
-            mock_scheduler.initialize_from_config.assert_called_once()
-
     @patch('vllm_ascend.platform.get_ascend_config')
     def test_get_attn_backend_cls_use_v1_and_mla(self, mock_get_ascend_config):
         mock_config = MagicMock()

tests/ut/test_utils.py

@@ -253,12 +253,10 @@ def test_update_aclgraph_sizes(self):
         model_path = os.path.join(os.path.dirname(__file__), "fake_weight")
         test_model_config = ModelConfig(model=model_path, enforce_eager=True)
         test_parallel_config = ParallelConfig()
-        ascend_config = {"ascend_scheduler_config": {"enabled": False}}
         test_vllm_config = VllmConfig(
             model_config=test_model_config,
             compilation_config=test_compilation_config,
-            parallel_config=test_parallel_config,
-            additional_config=ascend_config)
+            parallel_config=test_parallel_config)
         utils.update_aclgraph_sizes(test_vllm_config)
         os.environ['HCCL_OP_EXPANSION_MODE'] = 'AIV'
         utils.update_aclgraph_sizes(test_vllm_config)

tests/ut/torchair/models/test_torchair_deepseek_v2.py

@@ -235,8 +235,6 @@ def test_torchair_deepseek_v2_mlp(mock_distributed, base_config):
                                 hidden_act="silu",
                                 quant_config=None)
     assert isinstance(mlp.act_fn, TorchairDeepseekV2SiluAndMul)
-    ascend_config = MagicMock()
-    ascend_config._ASCEND_CONFIG.ascend_scheduler_config.enabled = False
     with patch(
             "vllm_ascend.torchair.models.torchair_deepseek_v2.QuantizationConfig"
     ) as mock_quant_config: