[UT] fix skip ut test for test_utils (#3803)

### What this PR does / why we need it?
[UT] fix ut test for test_utils that
https://github.com/vllm-project/vllm-ascend/pull/3612 skipped.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
vLLM version: v0.11.0rc3
vLLM main:
17c540a993

- vLLM version: v0.11.0rc3
- vLLM main:
83f478bb19

---------

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

.github/workflows/vllm_ascend_test.yaml

@@ -120,9 +120,7 @@ jobs:
           export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib
           pytest -sv --cov --cov-report=xml:unittests-coverage.xml tests/ut \
             --ignore tests/ut/torchair/models/test_torchair_deepseek_mtp.py \
-            --ignore tests/ut/torchair/models/test_torchair_deepseek_v2.py \
+            --ignore tests/ut/torchair/models/test_torchair_deepseek_v2.py
-            --ignore tests/ut/test_utils.py \
-            --ignore tests/ut/test_platform.py
 
       - name: Upload coverage to Codecov
         # only upload coverage when commits merged

tests/ut/test_platform.py

@@ -359,7 +359,7 @@ class TestNPUPlatform(TestBase):
             if vllm_version_is("0.11.0"):
                 self.assertEqual(
                     vllm_config.compilation_config.level,
-                    CompilationMode.NONE,
+                    CompilationLevel.NO_COMPILATION,
                 )
             else:
                 self.assertEqual(

tests/ut/test_utils.py

@@ -29,6 +29,12 @@ from vllm_ascend.utils import REGISTERED_ASCEND_OPS
 
 class TestUtils(TestBase):
 
+    def setUp(self):
+        import importlib
+
+        from vllm_ascend import platform
+        importlib.reload(platform)
+
     def test_is_310p(self):
         utils._IS_310P = None
         with mock.patch("vllm_ascend._build_info.__soc_version__",
@@ -252,16 +258,12 @@ class TestUtils(TestBase):
         self.assertIn("num_hidden_layers", str(context.exception))
 
     def test_update_aclgraph_sizes(self):
-        # max_num_batch_sizes < len(original_sizes)
         test_compilation_config = CompilationConfig(
             cudagraph_capture_sizes=[i for i in range(150)])
         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 = mock.MagicMock()
+        ascend_config = {"ascend_scheduler_config": {"enabled": False}}
-        ascend_config.max_num_batched_tokens = 2048
-        ascend_config.max_model_len = 1024
-        ascend_config.ascend_scheduler_config.enabled = False
         test_vllm_config = VllmConfig(
             model_config=test_model_config,
             compilation_config=test_compilation_config,
@@ -271,9 +273,18 @@ class TestUtils(TestBase):
         os.environ['HCCL_OP_EXPANSION_MODE'] = 'AIV'
         utils.update_aclgraph_sizes(test_vllm_config)
         del os.environ['HCCL_OP_EXPANSION_MODE']
-        self.assertEqual(
+
-            137,
+        if utils.vllm_version_is("0.11.0"):
-            len(test_vllm_config.compilation_config.cudagraph_capture_sizes))
+            self.assertEqual(
+                137,
+                len(test_vllm_config.compilation_config.cudagraph_capture_sizes
+                    ))
+        else:
+            self.assertEqual(
+                0,
+                len(test_vllm_config.compilation_config.cudagraph_capture_sizes
+                    ))
+            return
 
         test_vllm_config.speculative_config = mock.MagicMock()
         test_vllm_config.speculative_config.num_speculative_tokens = 2