[refactor] refactor model runner capture model (#5230)

### What this PR does / why we need it?
Refactor the `capture_model` method in model_runner to directly reuse
the method from vLLM.

Currently, most of the logic in the capture_model method is similar to
that in the vllm code. Directly using the vllm method can reduce the
maintenance cost of the vllm-ascend code. Modify as follows:
1、refactor capture_model function, directly inheriting community methods
2、refactor initialize_aclgraph_capture function, move to
initialize_attn_backend

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?

- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>

vllm_ascend/attention/attention_cp.py

@@ -44,9 +44,6 @@ from vllm_ascend.utils import weak_ref_tensors
 
 
 class AscendAttentionCPMetadataBuilder(AscendAttentionMetadataBuilder):
-    # Does this backend/builder support ACL Graphs for attention (default: no).
-    aclgraph_support: ClassVar[AttentionCGSupport] = \
-        AttentionCGSupport.ALWAYS
     # AttentionCGSupport.UNIFORM_SINGLE_TOKEN_DECODE
     # Does this backend/builder reorder the batch?
     # If not, set this to None. Otherwise set it to the query
@@ -72,6 +69,16 @@ class AscendAttentionCPMetadataBuilder(AscendAttentionMetadataBuilder):
         self.dcp_rank = get_decode_context_model_parallel_rank(
         ) if self.dcp_size > 1 else 0
 
+    @classmethod
+    def get_cudagraph_support(
+        cls: type["AscendAttentionCPMetadataBuilder"],
+        vllm_config: VllmConfig,
+        kv_cache_spec: AttentionSpec,
+    ) -> AttentionCGSupport:
+        # Explicit override in case the underlying builder specialized this getter.
+        # @override omitted only because of mypy limitation due to type variable.
+        return AttentionCGSupport.ALWAYS
+
     def _get_chunked_req_mask(self, local_context_lens_allranks) -> List[bool]:
         """
         given 4-d list [req][pcp][dcp], return: