[Bugfix] Fix num_hidden_layers when Qwen2-Audio 7B (#1803)

### What this PR does / why we need it?
Fix num_hidden_layers when Qwen2-Audio 7B and #1760 ：
```
INFO 07-15 04:38:53 [platform.py:174] PIECEWISE compilation enabled on NPU. use_inductor not supported - using only ACL Graph mode
Traceback (most recent call last):
  File "/workspace/test1.py", line 58, in <module>
    main(audio_count)
  File "/workspace/test1.py", line 38, in main
    llm = LLM(model="Qwen/Qwen2-Audio-7B-Instruct",
  File "/vllm-workspace/vllm/vllm/entrypoints/llm.py", line 271, in __init__
    self.llm_engine = LLMEngine.from_engine_args(
  File "/vllm-workspace/vllm/vllm/engine/llm_engine.py", line 494, in from_engine_args
    vllm_config = engine_args.create_engine_config(usage_context)
  File "/vllm-workspace/vllm/vllm/engine/arg_utils.py", line 1286, in create_engine_config
    config = VllmConfig(
  File "/usr/local/python3.10.17/lib/python3.10/site-packages/pydantic/_internal/_dataclasses.py", line 123, in __init__
    s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
  File "/vllm-workspace/vllm/vllm/config.py", line 4624, in __post_init__
    current_platform.check_and_update_config(self)
  File "/vllm-workspace/vllm-ascend/vllm_ascend/platform.py", line 180, in check_and_update_config
    update_aclgraph_sizes(vllm_config)
  File "/vllm-workspace/vllm-ascend/vllm_ascend/utils.py", line 307, in update_aclgraph_sizes
    num_hidden_layers = vllm_config.model_config.hf_config.num_hidden_layers
  File "/usr/local/python3.10.17/lib/python3.10/site-packages/transformers/configuration_utils.py", line 211, in __getattribute__
    return super().__getattribute__(key)
AttributeError: 'Qwen2AudioConfig' object has no attribute 'num_hidden_layers'
```

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

Closes: https://github.com/vllm-project/vllm-ascend/issues/1780
https://github.com/vllm-project/vllm-ascend/issues/1760
https://github.com/vllm-project/vllm-ascend/issues/1276
https://github.com/vllm-project/vllm-ascend/issues/359

- vLLM version: v0.10.0
- vLLM main:
7728dd77bb

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

vllm_ascend/utils.py

@@ -288,6 +288,24 @@ def vllm_version_is(target_vllm_version: str):
             "format of x.y.z.")
 
 
+def get_max_hidden_layers(hf_config) -> int:
+    cfg_dict = hf_config.to_dict()
+    layer_counts = []
+
+    def _rec_find(d):
+        if isinstance(d, dict):
+            for k, v in d.items():
+                if k == "num_hidden_layers" and isinstance(v, int):
+                    layer_counts.append(v)
+                else:
+                    _rec_find(v)
+
+    _rec_find(cfg_dict)
+    if not layer_counts:
+        raise ValueError("Not found num_hidden_layers in model config.")
+    return max(layer_counts)
+
+
 def update_aclgraph_sizes(vllm_config: VllmConfig) -> None:
     """Update ACL graph capture sizes based on hardware limitations"""
     # Store original configuration and temporarily clear it
@@ -296,7 +314,11 @@ def update_aclgraph_sizes(vllm_config: VllmConfig) -> None:
         compilation_config.cudagraph_capture_sizes, None
 
     # Calculate parallel configuration factor
-    num_hidden_layers = vllm_config.model_config.hf_config.num_hidden_layers
+    hf_config = vllm_config.model_config.hf_config
+    if hasattr(hf_config, 'num_hidden_layers'):
+        num_hidden_layers = hf_config.num_hidden_layers
+    else:
+        num_hidden_layers = get_max_hidden_layers(hf_config)
     parallel_config = vllm_config.parallel_config
 
     # TODO: Find out whether we need to take into account the pp_size