[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/compilation/acl_graph.py

@@ -296,8 +296,9 @@ def _update_attn_fia_params(update_stream, forward_context, runtime_shape):
             event.record(update_stream)
 
 
-def update_attn_params(update_stream, forward_context, runtime_shape):
-    if using_paged_attention(runtime_shape):
+def update_attn_params(update_stream, forward_context, runtime_shape,
+                       vllm_config):
+    if using_paged_attention(runtime_shape, vllm_config):
         _update_attn_pa_params(update_stream, forward_context, runtime_shape)
     else:
         _update_attn_fia_params(update_stream, forward_context, runtime_shape)

vllm_ascend/compilation/passes/qknorm_rope_fusion_pass.py

@@ -23,8 +23,7 @@ from torch._inductor.pattern_matcher import (PatternMatcherPass,
                                              PatternPrettyPrinter)
 from vllm.attention.layer import Attention
 from vllm.compilation.vllm_inductor_pass import VllmInductorPass
-from vllm.config import (VllmConfig, get_current_vllm_config,
-                         get_layers_from_vllm_config)
+from vllm.config import VllmConfig, get_layers_from_vllm_config
 
 
 class QKNormRopeFusionPattern:
@@ -42,7 +41,6 @@ class QKNormRopeFusionPattern:
         self.q_size = self.num_heads * self.head_dim
         self.kv_size = self.num_kv_heads * self.head_dim
         self.eps = eps
-        vllm_config = get_current_vllm_config()
         self.device = vllm_config.device_config.device if vllm_config.device_config else None
 
     def get_inputs(self):