Drop vLLM 0.13.0 support (#6069)

### What this PR does / why we need it?
Drop vLLM 0.13.0 support, upgrade to 0.14.0

- vLLM version: v0.13.0
- vLLM main:
d68209402d

---------

Signed-off-by: hfadzxy <starmoon_zhang@163.com>

tests/ut/attention/test_mla_v1.py

@@ -17,7 +17,6 @@ from vllm_ascend.attention.mla_v1 import (AscendMLABackend,
                                           AscendMLAPrefillMetadata,
                                           ChunkedContextMetadata)
 from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
-from vllm_ascend.utils import vllm_version_is
 
 
 class TestAscendMLABackend(TestBase):
@@ -477,10 +476,7 @@ class TestAscendMLAMetadataBuilderBuild(TestBase):
         self.mock_vllm_config.model_config = model_config
         self.kv_cache_spec = MagicMock()
         self.kv_cache_spec.num_layers = 32
-        if vllm_version_is('0.13.0'):
-            self.kv_cache_spec.head_size = 128
-        else:
-            self.kv_cache_spec.head_size = 64
+        self.kv_cache_spec.head_size = 64
         self.kv_cache_spec.num_heads = 32
 
     def tearDown(self):

tests/ut/test_platform.py

@@ -5,17 +5,11 @@ import pytest
 import torch
 from vllm.config.compilation import CompilationMode, CUDAGraphMode
 from vllm.platforms import PlatformEnum
+from vllm.v1.attention.selector import AttentionSelectorConfig  # type: ignore
 
 from tests.ut.base import TestBase
 from vllm_ascend.platform import NPUPlatform
-from vllm_ascend.utils import ASCEND_QUANTIZATION_METHOD, COMPRESSED_TENSORS_METHOD, AscendDeviceType, vllm_version_is
-
-# isort: off
-if vllm_version_is("0.13.0"):
-    from vllm.attention.selector import AttentionSelectorConfig  # type: ignore
-else:
-    from vllm.v1.attention.selector import AttentionSelectorConfig  # type: ignore
-# isort: on
+from vllm_ascend.utils import ASCEND_QUANTIZATION_METHOD, COMPRESSED_TENSORS_METHOD, AscendDeviceType 
 
 
 class TestNPUPlatform(TestBase):

tests/ut/worker/test_worker_v1.py

@@ -5,7 +5,6 @@ import torch
 from vllm.config import CacheConfig, ModelConfig, ParallelConfig, ProfilerConfig, VllmConfig
 
 from tests.ut.base import TestBase
-from vllm_ascend.utils import vllm_version_is
 
 init_cached_hf_modules_path = "vllm.utils.import_utils.init_cached_hf_modules"
 
@@ -141,10 +140,7 @@ class TestNPUWorker(TestBase):
         )
 
         # Verify init_cached_hf_modules is called (trust_remote_code=True)
-        if vllm_version_is('0.13.0'):
-            mock_init_cached_hf_modules.assert_called_once()
-        else:
-            mock_init_cached_hf_modules.assert_not_called()
+        mock_init_cached_hf_modules.assert_not_called()
 
     @patch("vllm_ascend.utils.adapt_patch")
     @patch("vllm_ascend.ops")