[Perf] Delete redundant operations in model_runner and forward_context (#3677)

### What this PR does / why we need it?

Remove redundant operations from `model_runner` and `forward_context`.
This optimization can significantly reduce the idle time (bubble) before
decoding when running models with small parameter counts (e.g.,
Qwen/Qwen2.5-0.5B).

Testing on 800I A2, bubble is reduced from 3.8ms to 2.8ms :
Before
<img width="1655" height="696" alt="image"
src="https://github.com/user-attachments/assets/d7608e52-2438-46dd-8fc9-391fd6274495"
/>

After
<img width="1607" height="774" alt="image"
src="https://github.com/user-attachments/assets/56daf081-2dba-4d2e-99d4-e055187d9806"
/>

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

### How was this patch tested?


- vLLM version: v0.11.0rc3
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.1

---------

Signed-off-by: realliujiaxu <realliujiaxu@163.com>

vllm_ascend/ascend_forward_context.py

@@ -11,7 +11,8 @@ from vllm.forward_context import (BatchDescriptor, get_forward_context,
                                   set_forward_context)
 
 import vllm_ascend.envs as envs_ascend
-from vllm_ascend.utils import enable_sp, is_moe_model, version_check
+from vllm_ascend.utils import (enable_sp, has_layer_idx, is_moe_model,
+                               version_check)
 
 if TYPE_CHECKING:
     from vllm_ascend.ops.weight_prefetch import WeightPrefetchMethod
@@ -137,9 +138,7 @@ def set_ascend_forward_context(
         # set layer_idx to enable optimization features that depend on this information.
         # This is only applicable to models that contain these necessary attributes.
         forward_context.layer_idx = None
-        if model_instance is not None and \
-            hasattr(model_instance, "model") and \
-            hasattr(model_instance.model, "start_layer"):
+        if has_layer_idx(model_instance):
             forward_context.layer_idx = model_instance.model.start_layer
 
         # TODO(rjg-lyh): refactor mlp weight prefetch method