[Bugfix] Fix num_hidden_layers when Qwen2-Audio 7B

[zhangxinyuehfad]

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: #1780 #1760 #1276 #359

• vLLM version: v0.10.0
• vLLM main: vllm-project/vllm@7728dd7

[codecov]

Codecov Report

❌ Patch coverage is 97.50000% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 73.26%. Comparing base (17a430f) to head (f764481).
⚠️ Report is 2 commits behind head on main.

Files with missing lines	Patch %	Lines
vllm_ascend/utils.py	94.11%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1803      +/-   ##
==========================================
+ Coverage   73.16%   73.26%   +0.09%     
==========================================
  Files          90       90              
  Lines        9929     9968      +39     
==========================================
+ Hits         7265     7303      +38     
- Misses       2664     2665       +1     

Flag	Coverage Δ
unittests	73.26% <97.50%> (+0.09%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[wangxiyuan]

Is there any e2e test to run this model?

[zhangxinyuehfad]

Is there any e2e test to run this model?

not yet, I will add it

[Yikun]

@yiz-liu @MengqingCao Please taking a look?

@zhangxinyuehfad Cloud you also have a test on: #1760

[zhangxinyuehfad]

@zhangxinyuehfad Cloud you also have a test on: #1760

yes, it also pass on Qwen/Qwen2.5-Omni-7B

[github-actions]

This pull request has conflicts, please resolve those before we can evaluate the pull request.

[Yikun]

LGTM.

BTW, I had an offline discuss with @ganyi1996ppo and @yiz-liu They also think this is an accept way to resolve the problem.