cleanup useless torchair logic (#4856)

This PR clean up useless torchair logic in model runner. The moge doc is
only for torchair, it can be removed as well.

- vLLM version: v0.12.0
- vLLM main:
vllm-project/vllm@ad32e3e

Signed-off-by: wangxiyuan <[email protected]>
Co-authored-by: Mengqing Cao <[email protected]>

Author: wangxiyuan

docs/source/tutorials/index.md

@@ -13,7 +13,6 @@ single_node_pd_disaggregation_mooncake
 multi_npu_qwen3_next
 multi_npu
 multi_npu_kimi-k2-thinking
-multi_npu_moge
 Qwen3-Dense
 multi_npu_qwen3_moe
 multi_npu_quantization

docs/source/tutorials/multi_npu_moge.md

@@ -229,7 +229,6 @@ def test_clear_npu_memory_reset_stats_failure(self, mock_reset_stats,
         mock_empty_cache.assert_called_once()
         mock_reset_stats.assert_called_once()
 
-    @patch("vllm_ascend.ascend_config.check_ascend_config")
     @patch("vllm_ascend.ascend_config.init_ascend_config")
     @patch("vllm_ascend.utils.update_aclgraph_sizes")
     @patch('vllm_ascend.utils.get_ascend_device_type',
@@ -240,7 +239,7 @@ def test_clear_npu_memory_reset_stats_failure(self, mock_reset_stats,
     )
     def test_check_and_update_config_basic_config_update(
             self, mock_init_recompute, mock_soc_version, mock_update_acl,
-            mock_init_ascend, mock_check_ascend):
+            mock_init_ascend):
         mock_init_ascend.return_value = TestNPUPlatform.mock_vllm_ascend_config(
         )
         vllm_config = TestNPUPlatform.mock_vllm_config()
@@ -263,18 +262,15 @@ def test_check_and_update_config_basic_config_update(
         self.platform.check_and_update_config(vllm_config)
 
         mock_init_ascend.assert_called_once_with(vllm_config)
-        mock_check_ascend.assert_called_once()
 
     @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_no_model_config_warning(
-            self, mock_init_recompute, mock_init_ascend, mock_check_ascend,
-            mock_soc_version):
+            self, mock_init_recompute, mock_init_ascend, mock_soc_version):
         mock_init_ascend.return_value = TestNPUPlatform.mock_vllm_ascend_config(
         )
         vllm_config = TestNPUPlatform.mock_vllm_config()
@@ -294,14 +290,12 @@ def test_check_and_update_config_no_model_config_warning(
 
     @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_enforce_eager_mode(
-            self, mock_init_recompute, mock_init_ascend, mock_check_ascend,
-            mock_soc_version):
+            self, mock_init_recompute, mock_init_ascend, mock_soc_version):
         mock_init_ascend.return_value = TestNPUPlatform.mock_vllm_ascend_config(
         )
         vllm_config = TestNPUPlatform.mock_vllm_config()
@@ -333,14 +327,13 @@ def test_check_and_update_config_enforce_eager_mode(
     @patch('vllm_ascend.utils.get_ascend_device_type',
            return_value=AscendDeviceType._910_93)
     @patch("vllm_ascend.utils.update_default_aclgraph_sizes")
-    @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_unsupported_compilation_level(
-            self, mock_init_recompute, mock_init_ascend, mock_check_ascend,
-            mock_update_default, mock_soc_version):
+            self, mock_init_recompute, mock_init_ascend, mock_update_default,
+            mock_soc_version):
         mock_update_default.return_value = MagicMock()
         mock_init_ascend.return_value = TestNPUPlatform.mock_vllm_ascend_config(
         )
@@ -374,10 +367,9 @@ def test_check_and_update_config_unsupported_compilation_level(
         "Revert me when vllm support setting cudagraph_mode on oot platform")
     @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")
     def test_check_and_update_config_unsupported_cudagraph_mode(
-            self, mock_init_ascend, mock_check_ascend, mock_soc_version):
+            self, mock_init_ascend, mock_soc_version):
         mock_init_ascend.return_value = TestNPUPlatform.mock_vllm_ascend_config(
         )
         vllm_config = TestNPUPlatform.mock_vllm_config()
@@ -404,14 +396,12 @@ def test_check_and_update_config_unsupported_cudagraph_mode(
 
     @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_cache_config_block_size(
-            self, mock_init_recompute, mock_init_ascend, mock_check_ascend,
-            mock_soc_version):
+            self, mock_init_recompute, mock_init_ascend, mock_soc_version):
         mock_init_ascend.return_value = TestNPUPlatform.mock_vllm_ascend_config(
         )
         vllm_config = TestNPUPlatform.mock_vllm_config()
@@ -433,14 +423,12 @@ def test_check_and_update_config_cache_config_block_size(
 
     @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_v1_worker_class_selection(
-            self, mock_init_recompute, mock_init_ascend, mock_check_ascend,
-            mock_soc_version):
+            self, mock_init_recompute, mock_init_ascend, mock_soc_version):
         mock_init_ascend.return_value = TestNPUPlatform.mock_vllm_ascend_config(
         )
         vllm_config = TestNPUPlatform.mock_vllm_config()
@@ -471,16 +459,14 @@ def test_check_and_update_config_v1_worker_class_selection(
             "vllm_ascend.xlite.xlite_worker.XliteWorker",
         )
 
-    @patch("vllm_ascend.ascend_config.check_ascend_config")
     @patch("vllm_ascend.ascend_config.init_ascend_config")
     @patch('vllm_ascend.utils.get_ascend_device_type',
            return_value=AscendDeviceType._310P)
     @patch(
         "vllm_ascend.core.recompute_schedule_config.RecomputeSchedulerConfig.initialize_from_config"
     )
     def test_check_and_update_config_310p_no_custom_ops(
-            self, mock_init_recompute, mock_soc_version, mock_init_ascend,
-            mock_check_ascend):
+            self, mock_init_recompute, mock_soc_version, mock_init_ascend):
         mock_init_ascend.return_value = TestNPUPlatform.mock_vllm_ascend_config(
         )
         vllm_config = TestNPUPlatform.mock_vllm_config()

tests/ut/test_platform.py

@@ -289,12 +289,3 @@ def get_ascend_config():
             "Ascend config is not initialized. Please call init_ascend_config first."
         )
     return _ASCEND_CONFIG
-
-
-def check_ascend_config(vllm_config, enforce_eager):
-    ascend_config = get_ascend_config()
-
-    if ascend_config.ascend_compilation_config.enable_quantization_fusion:
-        logger.info(
-            "Quantization fusion enabled! op fusion on quantization are expected. "
-        )