[Usage]:

[2019210489cqupt]

Your current environment

transformers==4.51.1
python==3.10
vllm==0.10.1

How would you like to use vllm

full output:
FireredASR-vLLM/examples/fireredasr_example.py

INFO 01-07 14:29:34 [init.py:241] Automatically detected platform cuda.
FireRedASR vLLM Integration Examples

3. Batch Transcription with Chunking (Memory-optimized)

---

This is the RECOMMENDED approach for large datasets (200+ files)
INFO 01-07 14:29:35 [utils.py:326] non-default args: {'model': '/home/dengjiaojiao.csby/FireRedASR/pretrained_models/FireRedASR-LLM-L/', 'tokenizer': '/home/dengjiaojiao.csby/FireRedASR/pretrained_models/tokenizer/', 'trust_remote_code': True, 'dtype': 'bfloat16', 'max_model_len': 4096, 'gpu_memory_utilization': 0.8, 'max_num_seqs': 32, 'disable_log_stats': True, 'mm_processor_cache_gb': 0}
The argument trust_remote_code is to be used with Auto classes. It has no effect here and is ignored.
Traceback (most recent call last):
File "/home/dengjiaojiao.csby/FireredASR-vLLM/examples/fireredasr_example.py", line 190, in
batch_transcription_with_chunking()
File "/home/dengjiaojiao.csby/FireredASR-vLLM/examples/fireredasr_example.py", line 83, in batch_transcription_with_chunking
llm = LLM(
File "/home/dengjiaojiao.csby/anaconda3/envs/req_env_py310/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 285, in init
self.llm_engine = LLMEngine.from_engine_args(
File "/home/dengjiaojiao.csby/anaconda3/envs/req_env_py310/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 483, in from_engine_args
vllm_config = engine_args.create_engine_config(usage_context)
File "/home/dengjiaojiao.csby/anaconda3/envs/req_env_py310/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 1057, in create_engine_config
model_config = self.create_model_config()
File "/home/dengjiaojiao.csby/anaconda3/envs/req_env_py310/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 904, in create_model_config
return ModelConfig(
File "/home/dengjiaojiao.csby/anaconda3/envs/req_env_py310/lib/python3.10/site-packages/pydantic/_internal/_dataclasses.py", line 123, in init
s.pydantic_validator.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
pydantic_core._pydantic_core.ValidationError: 1 validation error for ModelConfig
Value error, The checkpoint you are trying to load has model type fireredasr but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command pip install --upgrade transformers. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command pip install git+https://github.com/huggingface/transformers.git [type=value_error, input_value=ArgsKwargs((), {'model': ...gits_processors': None}), input_type=ArgsKwargs]
For further information visit https://errors.pydantic.dev/2.11/v/value_error

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[PatchouliTIS]

Refer to FireRedTeam/FireRedASR#50

[PatchouliTIS]

Hi @2019210489cqupt ， Have you successfully run FireredASR-vLLM since then? Did you encounter any additional issues?