r1.1 部署问题 #18
Description
按照中本地部署，出现下面的错误，可以帮忙看下吗
https://huggingface.co/stepfun-ai/Step-Audio-R1.1
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] Error in inspecting model architecture 'StepAudio2ForCausalLM'
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] Traceback (most recent call last):
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/models/registry.py", line 1196, in _run_in_subprocess
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] returned.check_returncode()
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/usr/lib/python3.10/subprocess.py", line 457, in check_returncode
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] raise CalledProcessError(self.returncode, self.args, self.stdout,
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] subprocess.CalledProcessError: Command '['/shared/siyuan/code/vllm/.venv/bin/python3', '-m', 'vllm.model_executor.models.registry']' returned non-zero exit status 1.
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772]
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] The above exception was the direct cause of the following exception:
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772]
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] Traceback (most recent call last):
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/models/registry.py", line 770, in _try_inspect_model_cls
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] return model.inspect_model_cls()
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/logging_utils/log_time.py", line 21, in _wrapper
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] result = func(*args, **kwargs)
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/models/registry.py", line 731, in inspect_model_cls
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] mi = _run_in_subprocess(
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/models/registry.py", line 1199, in _run_in_subprocess
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] raise RuntimeError(
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] RuntimeError: Error raised in subprocess:
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] /usr/lib/python3.10/runpy.py:126: RuntimeWarning: 'vllm.model_executor.models.registry' found in sys.modules after import of package 'vllm.model_executor.models', but prior to execution of 'vllm.model_executor.models.registry'; this may result in unpredictable behaviour
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] warn(RuntimeWarning(msg))
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] Traceback (most recent call last):
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] return _run_code(code, main_globals, None,
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] exec(code, run_globals)
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/models/registry.py", line 1222, in
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] _run()
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/models/registry.py", line 1215, in _run
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] result = fn()
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/models/registry.py", line 732, in
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] lambda: _ModelInfo.from_model_cls(self.load_model_cls())
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/models/registry.py", line 745, in load_model_cls
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] mod = importlib.import_module(self.module_name)
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/usr/lib/python3.10/importlib/init.py", line 126, in import_module
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] return _bootstrap._gcd_import(name[level:], package, level)
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "", line 1050, in _gcd_import
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "", line 1027, in _find_and_load
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "", line 1006, in _find_and_load_unlocked
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "", line 688, in _load_unlocked
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "", line 883, in exec_module
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "", line 241, in _call_with_frames_removed
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/models/mm_step_audio.py", line 15, in
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] from vllm.model_executor.model_loader.weight_utils import default_weight_loader
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/model_loader/init.py", line 11, in
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] from vllm.model_executor.model_loader.base_loader import BaseModelLoader
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/model_loader/base_loader.py", line 12, in
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] from vllm.model_executor.model_loader.utils import (
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/model_executor/model_loader/utils.py", line 14, in
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] from vllm.attention.layer import Attention, MLAAttention
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] File "/shared/siyuan/code/vllm/vllm/attention/layer.py", line 175
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] use_alibi_sqrt: bool | None = None,
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772] SyntaxError: duplicate argument 'use_alibi_sqrt' in function definition
(APIServer pid=634300) ERROR 01-18 13:10:59 [registry.py:772]
(APIServer pid=634300) Traceback (most recent call last):
(APIServer pid=634300) File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
(APIServer pid=634300) return _run_code(code, main_globals, None,
(APIServer pid=634300) File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
(APIServer pid=634300) exec(code, run_globals)
(APIServer pid=634300) File "/shared/siyuan/code/vllm/vllm/entrypoints/openai/api_server.py", line 991, in
(APIServer pid=634300) uvloop.run(run_server(args))
(APIServer pid=634300) File "/shared/siyuan/code/vllm/.venv/lib/python3.10/site-packages/uvloop/init.py", line 69, in run
(APIServer pid=634300) return loop.run_until_complete(wrapper())
(APIServer pid=634300) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(APIServer pid=634300) File "/shared/siyuan/code/vllm/.venv/lib/python3.10/site-packages/uvloop/init.py", line 48, in wrapper
(APIServer pid=634300) return await main
(APIServer pid=634300) File "/shared/siyuan/code/vllm/vllm/entrypoints/openai/api_server.py", line 920, in run_server
(APIServer pid=634300) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
(APIServer pid=634300) File "/shared/siyuan/code/vllm/vllm/entrypoints/openai/api_server.py", line 939, in run_server_worker
(APIServer pid=634300) async with build_async_engine_client(
(APIServer pid=634300) File "/usr/lib/python3.10/contextlib.py", line 199, in aenter
(APIServer pid=634300) return await anext(self.gen)
(APIServer pid=634300) File "/shared/siyuan/code/vllm/vllm/entrypoints/openai/api_server.py", line 146, in build_async_engine_client
(APIServer pid=634300) async with build_async_engine_client_from_engine_args(
(APIServer pid=634300) File "/usr/lib/python3.10/contextlib.py", line 199, in aenter
(APIServer pid=634300) return await anext(self.gen)
(APIServer pid=634300) File "/shared/siyuan/code/vllm/vllm/entrypoints/openai/api_server.py", line 172, in build_async_engine_client_from_engine_args
(APIServer pid=634300) vllm_config = engine_args.create_engine_config(usage_context=usage_context)
(APIServer pid=634300) File "/shared/siyuan/code/vllm/vllm/engine/arg_utils.py", line 1367, in create_engine_config
(APIServer pid=634300) model_config = self.create_model_config()
(APIServer pid=634300) File "/shared/siyuan/code/vllm/vllm/engine/arg_utils.py", line 1221, in create_model_config
(APIServer pid=634300) return ModelConfig(
(APIServer pid=634300) File "/shared/siyuan/code/vllm/.venv/lib/python3.10/site-packages/pydantic/_internal/_dataclasses.py", line 121, in init
(APIServer pid=634300) s.pydantic_validator.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
(APIServer pid=634300) pydantic_core._pydantic_core.ValidationError: 1 validation error for ModelConfig
(APIServer pid=634300) Value error, Model architectures ['StepAudio2ForCausalLM'] failed to be inspected. Please check the logs for more details. [type=value_error, input_value=ArgsKwargs((), {'model': ..., 'audio_parser': None}), input_type=ArgsKwargs]
(APIServer pid=634300) For further information visit https://errors.pydantic.dev/2.12/v/value_error