推理时报错：TypeError: AsyncEngineArgs.__init__() got an unexpected keyword argument 'device'

[Artanisax]

如题，是否是因为vllm版本过高了呢？

[FlashTTS] 2025-09-01 20:07:35 [INFO] [infer:65] >> Start up FlashTTS to perform inference.
[FlashTTS] 2025-09-01 20:07:35 [INFO] [infer:66] >> Inference args: Namespace(input='./test.txt', output='demo.wav', name=None, reference_audio=None, reference_text=None, latent_file=None, model_path='./models/SparkAudio/Spark-TTS-0.5B', backend='vllm', lang=None, llm_tensorrt_path=None, snac_path=None, llm_device='auto', tokenizer_device='auto', detokenizer_device='auto', wav2vec_attn_implementation='eager', llm_attn_implementation='eager', max_length=32768, llm_gpu_memory_utilization=0.6, torch_dtype='auto', cache_implementation=None, seed=0, batch_size=1, llm_batch_size=8, wait_timeout=0.01, pitch=None, speed=None, temperature=0.9, top_k=50, top_p=0.95, repetition_penalty=1.0, max_tokens=4096, func=<function infer_command_factory at 0x700c2ffed510>)
[FlashTTS] 2025-09-01 20:07:35 [INFO] [infer:68] >> Loading model from ./models/SparkAudio/Spark-TTS-0.5B...
[FlashTTS] 2025-09-01 20:07:35 [INFO] [auto_engine:120] >> Initializing `AutoEngine(engine=spark)` with config: (model_path='./models/SparkAudio/Spark-TTS-0.5B', max_length=32768, llm_device='auto', llm_tensorrt_path=None, backend='vllm', llm_attn_implementation='eager', torch_dtype='auto', llm_gpu_memory_utilization=0.6, cache_implementation=None, batch_size=1, llm_batch_size=8, seed=0, tokenizer_device='auto', detokenizer_device='auto', wav2vec_attn_implementation='eager', wait_timeout=0.01)
/home/artanisax/.local/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:143: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.
  WeightNorm.apply(module, name, dim)
INFO 09-01 20:07:40 [__init__.py:241] Automatically detected platform cuda.
Traceback (most recent call last):
  File "/home/artanisax/.local/bin/flashtts", line 8, in <module>
    sys.exit(main())
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/commands/flashtts_cli.py", line 31, in main
    service = args.func(args)
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/commands/infer.py", line 16, in infer_command_factory
    return InferCommand(args)
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/commands/infer.py", line 69, in __init__
    self.engine = AutoEngine(
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/engine/auto_engine.py", line 122, in __init__
    self._engine = engine_cls(**engine_kwargs)
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/engine/spark_engine.py", line 285, in __init__
    super().__init__(
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/engine/base_engine.py", line 177, in __init__
    self.generator = initialize_llm(
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/llm/init_llm.py", line 39, in initialize_llm
    return VllmGenerator(
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/llm/vllm_generator.py", line 32, in __init__
    async_args = AsyncEngineArgs(**engine_kwargs)
TypeError: AsyncEngineArgs.__init__() got an unexpected keyword argument 'device'
Exception ignored in: <function BaseEngine.__del__ at 0x700c4a0e51b0>
Traceback (most recent call last):
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/engine/base_engine.py", line 249, in __del__
    self.shutdown()
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/engine/base_engine.py", line 246, in shutdown
    self.generator.shutdown()
AttributeError: 'AsyncSparkEngine' object has no attribute 'generator'
Exception ignored in: <function AutoEngine.__del__ at 0x700c4a0e5990>
Traceback (most recent call last):
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/engine/auto_engine.py", line 144, in __del__
    self.shutdown()
  File "/home/artanisax/.local/lib/python3.10/site-packages/flashtts/engine/auto_engine.py", line 141, in shutdown
    self._engine.shutdown()
AttributeError: 'AutoEngine' object has no attribute '_engine'

[kvikk]

Downgrade vllm to 0.9.2 or comment out device in https://github.com/HuiResearch/FlashTTS/blob/master/flashtts/llm/vllm_generator.py#L27 if installing form source.