[BugFix]Fix incorrect get_current_vllm_config (#5121)

### What this PR does / why we need it?
This PR fixes some incorrect `get_current_vllm_config` calling, which
creates empty vllm_config instead.

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

### How was this patch tested?

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: Angazenn <supperccell@163.com>

vllm_ascend/attention/attention_v1.py

@@ -367,6 +367,7 @@ class AscendAttentionBackendImpl(AttentionImpl):
         kv_sharing_target_layer_name: Optional[str],
         **kwargs,
     ) -> None:
+        self.vllm_config = get_current_vllm_config()
         self.num_heads = num_heads
         self.head_size = head_size
         self.scale = float(scale)
@@ -723,7 +724,7 @@ class AscendAttentionBackendImpl(AttentionImpl):
     ):
         num_tokens = query.shape[0]
         if (attn_metadata.attn_state == AscendAttentionState.DecodeOnly
-                and using_paged_attention(num_tokens)
+                and using_paged_attention(num_tokens, self.vllm_config)
                 and self.sliding_window is None):
             output = self.forward_paged_attention(query, attn_metadata, output)
         else: