TypeError: cannot unpack non-iterable bool object 使用docker 镜像启动 报错 #2980
Description
A100 80G
使用fastdeploy启动ernie多模态大模型报错：
启动命令：python -m fastdeploy.entrypoints.openai.api_server --model /baidu/ERNIE-4.5-VL-28B-A3B-Paddle --port 8180 --metrics-port 8181 --engine-worker-queue-port 8182
--max-model-len 32768 --enable-mm --reasoning-parser ernie-45-vl --max-num-seqs 32
镜像：ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-cuda-12.6:2.0.0
/usr/local/lib/python3.10/dist-packages/_distutils_hack/init.py:30: UserWarning: Setuptools is replacing distutils. Support for replacing an already imported distutils is deprecated. In the future, this condition will fail. Register concerns at https://github.com/pypa/setuptools/issues/new?template=distutils-deprecation.yml
warnings.warn(
Traceback (most recent call last):
File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.10/dist-packages/fastdeploy/entrypoints/openai/api_server.py", line 385, in
main()
File "/usr/local/lib/python3.10/dist-packages/fastdeploy/entrypoints/openai/api_server.py", line 376, in main
if load_engine() is None:
File "/usr/local/lib/python3.10/dist-packages/fastdeploy/entrypoints/openai/api_server.py", line 85, in load_engine
if not engine.start(api_server_pid=os.getpid()):
File "/usr/local/lib/python3.10/dist-packages/fastdeploy/engine/engine.py", line 188, in start
self.data_processor = self.input_processor.create_processor()
File "/usr/local/lib/python3.10/dist-packages/fastdeploy/input/preprocess.py", line 92, in create_processor
self.processor = ErnieMoEVLProcessor(
File "/usr/local/lib/python3.10/dist-packages/fastdeploy/input/ernie_vl_processor.py", line 41, in init
self.ernie_processor = DataProcessor(
File "/usr/local/lib/python3.10/dist-packages/fastdeploy/input/mm_processor/process.py", line 104, in init
self._load_tokenizer()
File "/usr/local/lib/python3.10/dist-packages/fastdeploy/input/mm_processor/process.py", line 434, in _load_tokenizer
self.tokenizer = ErnieBotTokenizer.from_pretrained(self.model_name_or_path)
File "/usr/local/lib/python3.10/dist-packages/paddleformers/transformers/tokenizer_utils.py", line 910, in from_pretrained
tokenizer, tokenizer_config_file_dir = super().from_pretrained(pretrained_model_name_or_path, *args, **kwargs)
TypeError: cannot unpack non-iterable bool object
