[Bug] ValueError: Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.

[dahwin]

Your current environment

I''m using two tesla t4

from vllm import LLM
from vllm.sampling_params import SamplingParams
import torch

MODEL_NAME = "Qwen/Qwen2-VL-7B-Instruct"

# Define the model and sampling parameters
MODEL_NAME = "Qwen/Qwen2.5-VL-7B-Instruct"
sampling_params = SamplingParams(max_tokens=300, temperature=0.01, top_p=0.001)

# Define context length and number of devices
context_length = 3000
num_device = 2

# Initialize the LLM with the allowed local media path
llm = LLM(
    model=MODEL_NAME,
    tokenizer=MODEL_NAME,
    speculative_max_model_len=context_length,
    max_seq_len_to_capture=context_length,
    max_model_len=context_length,
    tensor_parallel_size=num_device,
    trust_remote_code=True,
    # worker_use_ray=num_device,
    dtype=torch.float16,
    enable_chunked_prefill=True,
    gpu_memory_utilization=0.90,
    enforce_eager=True,
    max_num_batched_tokens=context_length,
    allowed_local_media_path="/kaggle/working/" # Add this line
    ,
     # quantization="fp8"

    # enable_prefix_caching=True,
    mm_processor_kwargs={"max_dynamic_patch": 1}
)

# Define the prompt and image path
prompt = "Describe this image in one sentence."
image_path = "file:///kaggle/working/dubu.png"  # Convert local path to file:// URI
# image_path = "file:///kaggle/working/image.png"  # Convert local path to file:// URI
# Create the structured input format
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": prompt
            },
            {
                "type": "image_url",
                "image_url": {
                    "url": image_path  # Use the file:// URI
                }
            },
        ],
    },
]



# Generate outputs
outputs = llm.chat(
    messages,
    sampling_params=sampling_params,
)


# Print the output
print(outputs[0].outputs[0].text)

INFO 02-08 02:36:39 __init__.py:190] Automatically detected platform cuda.
config.json: 100%
 1.37k/1.37k [00:00<00:00, 127kB/s]
preprocessor_config.json: 100%
 353/353 [00:00<00:00, 38.2kB/s]
WARNING 02-08 02:36:40 config.py:2386] Casting torch.bfloat16 to torch.float16.
ERROR 02-08 02:36:50 registry.py:306] Error in inspecting model architecture 'Qwen2_5_VLForConditionalGeneration'
ERROR 02-08 02:36:50 registry.py:306] Traceback (most recent call last):
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 507, in _run_in_subprocess
ERROR 02-08 02:36:50 registry.py:306]     returned.check_returncode()
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/lib/python3.10/subprocess.py", line 457, in check_returncode
ERROR 02-08 02:36:50 registry.py:306]     raise CalledProcessError(self.returncode, self.args, self.stdout,
ERROR 02-08 02:36:50 registry.py:306] subprocess.CalledProcessError: Command '['/usr/bin/python3', '-m', 'vllm.model_executor.models.registry']' returned non-zero exit status 1.
ERROR 02-08 02:36:50 registry.py:306] 
ERROR 02-08 02:36:50 registry.py:306] The above exception was the direct cause of the following exception:
ERROR 02-08 02:36:50 registry.py:306] 
ERROR 02-08 02:36:50 registry.py:306] Traceback (most recent call last):
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 304, in _try_inspect_model_cls
ERROR 02-08 02:36:50 registry.py:306]     return model.inspect_model_cls()
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 275, in inspect_model_cls
ERROR 02-08 02:36:50 registry.py:306]     return _run_in_subprocess(
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 510, in _run_in_subprocess
ERROR 02-08 02:36:50 registry.py:306]     raise RuntimeError(f"Error raised in subprocess:\n"
ERROR 02-08 02:36:50 registry.py:306] RuntimeError: Error raised in subprocess:
ERROR 02-08 02:36:50 registry.py:306] 2025-02-08 02:36:45.612461: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
ERROR 02-08 02:36:50 registry.py:306] 2025-02-08 02:36:45.633154: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
ERROR 02-08 02:36:50 registry.py:306] 2025-02-08 02:36:45.639437: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
ERROR 02-08 02:36:50 registry.py:306] /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
ERROR 02-08 02:36:50 registry.py:306]   warn(RuntimeWarning(msg))
ERROR 02-08 02:36:50 registry.py:306] Traceback (most recent call last):
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
ERROR 02-08 02:36:50 registry.py:306]     return _run_code(code, main_globals, None,
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
ERROR 02-08 02:36:50 registry.py:306]     exec(code, run_globals)
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 531, in <module>
ERROR 02-08 02:36:50 registry.py:306]     _run()
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 524, in _run
ERROR 02-08 02:36:50 registry.py:306]     result = fn()
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 276, in <lambda>
ERROR 02-08 02:36:50 registry.py:306]     lambda: _ModelInfo.from_model_cls(self.load_model_cls()))
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 279, in load_model_cls
ERROR 02-08 02:36:50 registry.py:306]     mod = importlib.import_module(self.module_name)
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/lib/python3.10/importlib/__init__.py", line 126, in import_module
ERROR 02-08 02:36:50 registry.py:306]     return _bootstrap._gcd_import(name[level:], package, level)
ERROR 02-08 02:36:50 registry.py:306]   File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
ERROR 02-08 02:36:50 registry.py:306]   File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
ERROR 02-08 02:36:50 registry.py:306]   File "<frozen importlib._bootstrap>", line 1006, in _find_and_load_unlocked
ERROR 02-08 02:36:50 registry.py:306]   File "<frozen importlib._bootstrap>", line 688, in _load_unlocked
ERROR 02-08 02:36:50 registry.py:306]   File "<frozen importlib._bootstrap_external>", line 883, in exec_module
ERROR 02-08 02:36:50 registry.py:306]   File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/qwen2_5_vl.py", line 51, in <module>
ERROR 02-08 02:36:50 registry.py:306]     from vllm.model_executor.layers.quantization.gptq import GPTQConfig
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/layers/quantization/gptq.py", line 15, in <module>
ERROR 02-08 02:36:50 registry.py:306]     from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/layers/vocab_parallel_embedding.py", line 139, in <module>
ERROR 02-08 02:36:50 registry.py:306]     def get_masked_input_and_mask(
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/torch/__init__.py", line 2424, in fn
ERROR 02-08 02:36:50 registry.py:306]     return compile(
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/torch/__init__.py", line 2447, in compile
ERROR 02-08 02:36:50 registry.py:306]     return torch._dynamo.optimize(
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py", line 716, in optimize
ERROR 02-08 02:36:50 registry.py:306]     return _optimize(rebuild_ctx, *args, **kwargs)
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py", line 790, in _optimize
ERROR 02-08 02:36:50 registry.py:306]     compiler_config=backend.get_compiler_config()
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/torch/__init__.py", line 2237, in get_compiler_config
ERROR 02-08 02:36:50 registry.py:306]     from torch._inductor.compile_fx import get_patched_config_dict
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/compile_fx.py", line 49, in <module>
ERROR 02-08 02:36:50 registry.py:306]     from torch._inductor.debug import save_args_for_compile_fx_inner
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/debug.py", line 26, in <module>
ERROR 02-08 02:36:50 registry.py:306]     from . import config, ir  # noqa: F811, this is needed
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/ir.py", line 77, in <module>
ERROR 02-08 02:36:50 registry.py:306]     from .runtime.hints import ReductionHint
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/runtime/hints.py", line 36, in <module>
ERROR 02-08 02:36:50 registry.py:306]     attr_desc_fields = {f.name for f in fields(AttrsDescriptor)}
ERROR 02-08 02:36:50 registry.py:306]   File "/usr/lib/python3.10/dataclasses.py", line 1198, in fields
ERROR 02-08 02:36:50 registry.py:306]     raise TypeError('must be called with a dataclass type or instance') from None
ERROR 02-08 02:36:50 registry.py:306] TypeError: must be called with a dataclass type or instance
ERROR 02-08 02:36:50 registry.py:306] 
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-1-28d98e80f319> in <cell line: 16>()
     14 
     15 # Initialize the LLM with the allowed local media path
---> 16 llm = LLM(
     17     model=MODEL_NAME,
     18     tokenizer=MODEL_NAME,

/usr/local/lib/python3.10/dist-packages/vllm/utils.py in inner(*args, **kwargs)
   1049                     )
   1050 
-> 1051             return fn(*args, **kwargs)
   1052 
   1053         return inner  # type: ignore

/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/llm.py in __init__(self, model, tokenizer, tokenizer_mode, skip_tokenizer_init, trust_remote_code, allowed_local_media_path, tensor_parallel_size, dtype, quantization, revision, tokenizer_revision, seed, gpu_memory_utilization, swap_space, cpu_offload_gb, enforce_eager, max_seq_len_to_capture, disable_custom_all_reduce, disable_async_output_proc, hf_overrides, mm_processor_kwargs, task, override_pooler_config, compilation_config, **kwargs)
    240         # to avoid import order issues
    241         self.engine_class = self.get_engine_class()
--> 242         self.llm_engine = self.engine_class.from_engine_args(
    243             engine_args, usage_context=UsageContext.LLM_CLASS)
    244 

/usr/local/lib/python3.10/dist-packages/vllm/engine/llm_engine.py in from_engine_args(cls, engine_args, usage_context, stat_loggers)
    479         """Creates an LLM engine from the engine arguments."""
    480         # Create the engine configs.
--> 481         engine_config = engine_args.create_engine_config(usage_context)
    482         executor_class = cls._get_executor_cls(engine_config)
    483         # Create the LLM engine.

/usr/local/lib/python3.10/dist-packages/vllm/engine/arg_utils.py in create_engine_config(self, usage_context)
   1073 
   1074         device_config = DeviceConfig(device=self.device)
-> 1075         model_config = self.create_model_config()
   1076 
   1077         if (model_config.is_multimodal_model and not envs.VLLM_USE_V1

/usr/local/lib/python3.10/dist-packages/vllm/engine/arg_utils.py in create_model_config(self)
    996 
    997     def create_model_config(self) -> ModelConfig:
--> 998         return ModelConfig(
    999             model=self.model,
   1000             task=self.task,

/usr/local/lib/python3.10/dist-packages/vllm/config.py in __init__(self, model, task, tokenizer, tokenizer_mode, trust_remote_code, dtype, seed, allowed_local_media_path, revision, code_revision, rope_scaling, rope_theta, tokenizer_revision, max_model_len, spec_target_max_model_len, quantization, enforce_eager, max_seq_len_to_capture, max_logprobs, disable_sliding_window, skip_tokenizer_init, served_model_name, limit_mm_per_prompt, use_async_output_proc, config_format, hf_overrides, mm_processor_kwargs, disable_mm_preprocessor_cache, override_neuron_config, override_pooler_config, logits_processor_pattern, generation_config, enable_sleep_mode, override_generation_config, model_impl)
    362         self.served_model_name = get_served_model_name(model,
    363                                                        served_model_name)
--> 364         self.multimodal_config = self._init_multimodal_config(
    365             limit_mm_per_prompt)
    366         if not self.skip_tokenizer_init:

/usr/local/lib/python3.10/dist-packages/vllm/config.py in _init_multimodal_config(self, limit_mm_per_prompt)
    422     ) -> Optional["MultiModalConfig"]:
    423         architectures = getattr(self.hf_config, "architectures", [])
--> 424         if ModelRegistry.is_multimodal_model(architectures):
    425             return MultiModalConfig(limit_per_prompt=limit_mm_per_prompt or {})
    426 

/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py in is_multimodal_model(self, architectures)
    443         architectures: Union[str, List[str]],
    444     ) -> bool:
--> 445         model_cls, _ = self.inspect_model_cls(architectures)
    446         return model_cls.supports_multimodal
    447 

/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py in inspect_model_cls(self, architectures)
    403                 return (model_info, arch)
    404 
--> 405         return self._raise_for_unsupported(architectures)
    406 
    407     def resolve_model_cls(

/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py in _raise_for_unsupported(self, architectures)
    355 
    356         if any(arch in all_supported_archs for arch in architectures):
--> 357             raise ValueError(
    358                 f"Model architectures {architectures} failed "
    359                 "to be inspected. Please check the logs for more details.")

ValueError: Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.
add Codeadd Markdown

🐛 Describe the bug

l

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.

[DarkLight1337]

Please refer to this section of the troubleshooting guide. It is likely that your triton version is not compatible with PyTorch

[dahwin]

thanks

[Aasthaengg]

Hi I'm facing the same issue and have checked with documentation as well; I've the correct triton version that is compatible - torch 2.5.1 with triton==3.1.0

[DarkLight1337]

Are you able to run this code?

import torch

@torch.compile
def f(x):
    # a simple function to test torch.compile
    x = x + 1
    x = x * 2
    x = x.sin()
    return x

x = torch.randn(4, 4).cuda()
print(f(x))

[RuiaRui]

Same error under A10 with Qwen2.5. I checked the triton version and can run the following code.

import torch
@torch.compile
def f(x):
    # a simple function to test torch.compile
    x = x + 1
    x = x * 2
    x = x.sin()
    return x

x = torch.randn(4, 4).cuda()
print(f(x))

[DarkLight1337]

Can you show the full stack trace you get in vLLM?

[mkvn-1]

INFO 02-17 09:29:26 __init__.py:190] Automatically detected platform cuda.
INFO 02-17 09:29:27 api_server.py:840] vLLM API server version 0.7.2
INFO 02-17 09:29:27 api_server.py:841] args: Namespace(subparser='serve', model_tag='Qwen/Qwen2.5-VL-7B-Instruct', config='', host=None, port=8000, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, enable_reasoning=False, reasoning_parser=None, tool_call_parser=None, tool_parser_plugin='', model='Qwen/Qwen2.5-VL-7B-Instruct', task='auto', tokenizer=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, allowed_local_media_path=None, download_dir=None, load_format='auto', config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', max_model_len=None, guided_decoding_backend='xgrammar', logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=4, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=None, enable_prefix_caching=None, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=0, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=False, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=None, qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', generation_config=None, override_generation_config=None, enable_sleep_mode=False, calculate_kv_scales=False, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, dispatch_function=<function serve at 0x72c332156f20>)
INFO 02-17 09:29:27 api_server.py:206] Started engine process with PID 3143
config.json: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.37k/1.37k [00:00<00:00, 15.1MB/s]preprocessor_config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 350/350 [00:00<00:00, 5.34MB/s]INFO 02-17 09:29:30 __init__.py:190] Automatically detected platform cuda.
ERROR 02-17 09:29:32 registry.py:306] Error in inspecting model architecture 'Qwen2_5_VLForConditionalGeneration'
ERROR 02-17 09:29:32 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 507, in _run_in_subprocess
ERROR 02-17 09:29:32 registry.py:306]     returned.check_returncode()
ERROR 02-17 09:29:32 registry.py:306]   File "/usr/lib/python3.12/subprocess.py", line 502, in check_returncode
ERROR 02-17 09:29:32 registry.py:306]     raise CalledProcessError(self.returncode, self.args, self.stdout,
ERROR 02-17 09:29:32 registry.py:306] subprocess.CalledProcessError: Command '['/usr/bin/python3', '-m', 'vllm.model_executor.models.registry']' returned non-zero exit status 1.
ERROR 02-17 09:29:32 registry.py:306] 
ERROR 02-17 09:29:32 registry.py:306] The above exception was the direct cause of the following exception:
ERROR 02-17 09:29:32 registry.py:306] 
ERROR 02-17 09:29:32 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 304, in _try_inspect_model_cls
ERROR 02-17 09:29:32 registry.py:306]     return model.inspect_model_cls()
ERROR 02-17 09:29:32 registry.py:306]            ^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 275, in inspect_model_cls
ERROR 02-17 09:29:32 registry.py:306]     return _run_in_subprocess(
ERROR 02-17 09:29:32 registry.py:306]            ^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 510, in _run_in_subprocess
ERROR 02-17 09:29:32 registry.py:306]     raise RuntimeError(f"Error raised in subprocess:\n"
ERROR 02-17 09:29:32 registry.py:306] RuntimeError: Error raised in subprocess:
ERROR 02-17 09:29:32 registry.py:306] <frozen runpy>:128: 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
ERROR 02-17 09:29:32 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen runpy>", line 198, in _run_module_as_main
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen runpy>", line 88, in _run_code
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 531, in <module>
ERROR 02-17 09:29:32 registry.py:306]     _run()
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 524, in _run
ERROR 02-17 09:29:32 registry.py:306]     result = fn()
ERROR 02-17 09:29:32 registry.py:306]              ^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 276, in <lambda>
ERROR 02-17 09:29:32 registry.py:306]     lambda: _ModelInfo.from_model_cls(self.load_model_cls()))
ERROR 02-17 09:29:32 registry.py:306]                                       ^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 279, in load_model_cls
ERROR 02-17 09:29:32 registry.py:306]     mod = importlib.import_module(self.module_name)
ERROR 02-17 09:29:32 registry.py:306]           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/usr/lib/python3.12/importlib/__init__.py", line 90, in import_module
ERROR 02-17 09:29:32 registry.py:306]     return _bootstrap._gcd_import(name[level:], package, level)
ERROR 02-17 09:29:32 registry.py:306]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 1387, in _gcd_import
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 1360, in _find_and_load
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 1331, in _find_and_load_unlocked
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 935, in _load_unlocked
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap_external>", line 995, in exec_module
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 36, in <module>
ERROR 02-17 09:29:32 registry.py:306]     from transformers.models.qwen2_5_vl import (Qwen2_5_VLImageProcessor,
ERROR 02-17 09:29:32 registry.py:306] ImportError: cannot import name 'Qwen2_5_VLImageProcessor' from 'transformers.models.qwen2_5_vl' (/home/itadmin/.local/lib/python3.12/site-packages/transformers/models/qwen2_5_vl/__init__.py). Did you mean: 'Qwen2_5_VLProcessor'?
ERROR 02-17 09:29:32 registry.py:306] 
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/scripts.py", line 210, in <module>
    main()
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/scripts.py", line 204, in main
    args.dispatch_function(args)
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/scripts.py", line 44, in serve
    uvloop.run(run_server(args))
  File "/home/itadmin/.local/lib/python3.12/site-packages/uvloop/__init__.py", line 109, in run
    return __asyncio.run(
           ^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/home/itadmin/.local/lib/python3.12/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
           ^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 875, in run_server
    async with build_async_engine_client(args) as engine_client:
  File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 136, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
  File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 217, in build_async_engine_client_from_engine_args
    engine_config = engine_args.create_engine_config()
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1075, in create_engine_config
    model_config = self.create_model_config()
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 998, in create_model_config
    return ModelConfig(
           ^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 364, in __init__
    self.multimodal_config = self._init_multimodal_config(
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 424, in _init_multimodal_config
    if ModelRegistry.is_multimodal_model(architectures):
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 445, in is_multimodal_model
    model_cls, _ = self.inspect_model_cls(architectures)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 405, in inspect_model_cls
    return self._raise_for_unsupported(architectures)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 357, in _raise_for_unsupported
    raise ValueError(
ValueError: Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.
ERROR 02-17 09:29:36 registry.py:306] Error in inspecting model architecture 'Qwen2_5_VLForConditionalGeneration'
ERROR 02-17 09:29:36 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 507, in _run_in_subprocess
ERROR 02-17 09:29:36 registry.py:306]     returned.check_returncode()
ERROR 02-17 09:29:36 registry.py:306]   File "/usr/lib/python3.12/subprocess.py", line 502, in check_returncode
ERROR 02-17 09:29:36 registry.py:306]     raise CalledProcessError(self.returncode, self.args, self.stdout,
ERROR 02-17 09:29:36 registry.py:306] subprocess.CalledProcessError: Command '['/usr/bin/python3', '-m', 'vllm.model_executor.models.registry']' returned non-zero exit status 1.
ERROR 02-17 09:29:36 registry.py:306] 
ERROR 02-17 09:29:36 registry.py:306] The above exception was the direct cause of the following exception:
ERROR 02-17 09:29:36 registry.py:306] 
ERROR 02-17 09:29:36 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 304, in _try_inspect_model_cls
ERROR 02-17 09:29:36 registry.py:306]     return model.inspect_model_cls()
ERROR 02-17 09:29:36 registry.py:306]            ^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 275, in inspect_model_cls
ERROR 02-17 09:29:36 registry.py:306]     return _run_in_subprocess(
ERROR 02-17 09:29:36 registry.py:306]            ^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 510, in _run_in_subprocess
ERROR 02-17 09:29:36 registry.py:306]     raise RuntimeError(f"Error raised in subprocess:\n"
ERROR 02-17 09:29:36 registry.py:306] RuntimeError: Error raised in subprocess:
ERROR 02-17 09:29:36 registry.py:306] <frozen runpy>:128: 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
ERROR 02-17 09:29:36 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen runpy>", line 198, in _run_module_as_main
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen runpy>", line 88, in _run_code
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 531, in <module>
ERROR 02-17 09:29:36 registry.py:306]     _run()
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 524, in _run
ERROR 02-17 09:29:36 registry.py:306]     result = fn()
ERROR 02-17 09:29:36 registry.py:306]              ^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 276, in <lambda>
ERROR 02-17 09:29:36 registry.py:306]     lambda: _ModelInfo.from_model_cls(self.load_model_cls()))
ERROR 02-17 09:29:36 registry.py:306]                                       ^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 279, in load_model_cls
ERROR 02-17 09:29:36 registry.py:306]     mod = importlib.import_module(self.module_name)
ERROR 02-17 09:29:36 registry.py:306]           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/usr/lib/python3.12/importlib/__init__.py", line 90, in import_module
ERROR 02-17 09:29:36 registry.py:306]     return _bootstrap._gcd_import(name[level:], package, level)
ERROR 02-17 09:29:36 registry.py:306]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 1387, in _gcd_import
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 1360, in _find_and_load
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 1331, in _find_and_load_unlocked
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 935, in _load_unlocked
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap_external>", line 995, in exec_module
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 36, in <module>
ERROR 02-17 09:29:36 registry.py:306]     from transformers.models.qwen2_5_vl import (Qwen2_5_VLImageProcessor,
ERROR 02-17 09:29:36 registry.py:306] ImportError: cannot import name 'Qwen2_5_VLImageProcessor' from 'transformers.models.qwen2_5_vl' (/home/itadmin/.local/lib/python3.12/site-packages/transformers/models/qwen2_5_vl/__init__.py). Did you mean: 'Qwen2_5_VLProcessor'?
ERROR 02-17 09:29:36 registry.py:306] 
ERROR 02-17 09:29:36 engine.py:389] Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.
ERROR 02-17 09:29:36 engine.py:389] Traceback (most recent call last):
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 380, in run_mp_engine
ERROR 02-17 09:29:36 engine.py:389]     engine = MQLLMEngine.from_engine_args(engine_args=engine_args,
ERROR 02-17 09:29:36 engine.py:389]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 118, in from_engine_args
ERROR 02-17 09:29:36 engine.py:389]     engine_config = engine_args.create_engine_config(usage_context)
ERROR 02-17 09:29:36 engine.py:389]                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1075, in create_engine_config
ERROR 02-17 09:29:36 engine.py:389]     model_config = self.create_model_config()
ERROR 02-17 09:29:36 engine.py:389]                    ^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 998, in create_model_config
ERROR 02-17 09:29:36 engine.py:389]     return ModelConfig(
ERROR 02-17 09:29:36 engine.py:389]            ^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 364, in __init__
ERROR 02-17 09:29:36 engine.py:389]     self.multimodal_config = self._init_multimodal_config(
ERROR 02-17 09:29:36 engine.py:389]                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 424, in _init_multimodal_config
ERROR 02-17 09:29:36 engine.py:389]     if ModelRegistry.is_multimodal_model(architectures):
ERROR 02-17 09:29:36 engine.py:389]        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 445, in is_multimodal_model
ERROR 02-17 09:29:36 engine.py:389]     model_cls, _ = self.inspect_model_cls(architectures)
ERROR 02-17 09:29:36 engine.py:389]                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 405, in inspect_model_cls
ERROR 02-17 09:29:36 engine.py:389]     return self._raise_for_unsupported(architectures)
ERROR 02-17 09:29:36 engine.py:389]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 357, in _raise_for_unsupported
ERROR 02-17 09:29:36 engine.py:389]     raise ValueError(
ERROR 02-17 09:29:36 engine.py:389] ValueError: Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.
Process SpawnProcess-1:
Traceback (most recent call last):
  File "/usr/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/usr/lib/python3.12/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 391, in run_mp_engine
    raise e
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 380, in run_mp_engine
    engine = MQLLMEngine.from_engine_args(engine_args=engine_args,
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 118, in from_engine_args
    engine_config = engine_args.create_engine_config(usage_context)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1075, in create_engine_config
    model_config = self.create_model_config()
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 998, in create_model_config
    return ModelConfig(
           ^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 364, in __init__
    self.multimodal_config = self._init_multimodal_config(
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 424, in _init_multimodal_config
    if ModelRegistry.is_multimodal_model(architectures):
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 445, in is_multimodal_model
    model_cls, _ = self.inspect_model_cls(architectures)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 405, in inspect_model_cls
    return self._raise_for_unsupported(architectures)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 357, in _raise_for_unsupported
    raise ValueError(
ValueError: Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.python3 -m vllm.scripts serve "Qwen/Qwen2.5-VL-7B-Instruct" --tensor-parallel-size 4
INFO 02-17 09:29:26 __init__.py:190] Automatically detected platform cuda.
INFO 02-17 09:29:27 api_server.py:840] vLLM API server version 0.7.2
INFO 02-17 09:29:27 api_server.py:841] args: Namespace(subparser='serve', model_tag='Qwen/Qwen2.5-VL-7B-Instruct', config='', host=None, port=8000, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, enable_reasoning=False, reasoning_parser=None, tool_call_parser=None, tool_parser_plugin='', model='Qwen/Qwen2.5-VL-7B-Instruct', task='auto', tokenizer=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, allowed_local_media_path=None, download_dir=None, load_format='auto', config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', max_model_len=None, guided_decoding_backend='xgrammar', logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=4, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=None, enable_prefix_caching=None, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=0, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=False, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=None, qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', generation_config=None, override_generation_config=None, enable_sleep_mode=False, calculate_kv_scales=False, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, dispatch_function=<function serve at 0x72c332156f20>)
INFO 02-17 09:29:27 api_server.py:206] Started engine process with PID 3143
config.json: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.37k/1.37k [00:00<00:00, 15.1MB/s]preprocessor_config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 350/350 [00:00<00:00, 5.34MB/s]INFO 02-17 09:29:30 __init__.py:190] Automatically detected platform cuda.
ERROR 02-17 09:29:32 registry.py:306] Error in inspecting model architecture 'Qwen2_5_VLForConditionalGeneration'
ERROR 02-17 09:29:32 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 507, in _run_in_subprocess
ERROR 02-17 09:29:32 registry.py:306]     returned.check_returncode()
ERROR 02-17 09:29:32 registry.py:306]   File "/usr/lib/python3.12/subprocess.py", line 502, in check_returncode
ERROR 02-17 09:29:32 registry.py:306]     raise CalledProcessError(self.returncode, self.args, self.stdout,
ERROR 02-17 09:29:32 registry.py:306] subprocess.CalledProcessError: Command '['/usr/bin/python3', '-m', 'vllm.model_executor.models.registry']' returned non-zero exit status 1.
ERROR 02-17 09:29:32 registry.py:306] 
ERROR 02-17 09:29:32 registry.py:306] The above exception was the direct cause of the following exception:
ERROR 02-17 09:29:32 registry.py:306] 
ERROR 02-17 09:29:32 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 304, in _try_inspect_model_cls
ERROR 02-17 09:29:32 registry.py:306]     return model.inspect_model_cls()
ERROR 02-17 09:29:32 registry.py:306]            ^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 275, in inspect_model_cls
ERROR 02-17 09:29:32 registry.py:306]     return _run_in_subprocess(
ERROR 02-17 09:29:32 registry.py:306]            ^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 510, in _run_in_subprocess
ERROR 02-17 09:29:32 registry.py:306]     raise RuntimeError(f"Error raised in subprocess:\n"
ERROR 02-17 09:29:32 registry.py:306] RuntimeError: Error raised in subprocess:
ERROR 02-17 09:29:32 registry.py:306] <frozen runpy>:128: 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
ERROR 02-17 09:29:32 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen runpy>", line 198, in _run_module_as_main
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen runpy>", line 88, in _run_code
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 531, in <module>
ERROR 02-17 09:29:32 registry.py:306]     _run()
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 524, in _run
ERROR 02-17 09:29:32 registry.py:306]     result = fn()
ERROR 02-17 09:29:32 registry.py:306]              ^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 276, in <lambda>
ERROR 02-17 09:29:32 registry.py:306]     lambda: _ModelInfo.from_model_cls(self.load_model_cls()))
ERROR 02-17 09:29:32 registry.py:306]                                       ^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 279, in load_model_cls
ERROR 02-17 09:29:32 registry.py:306]     mod = importlib.import_module(self.module_name)
ERROR 02-17 09:29:32 registry.py:306]           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "/usr/lib/python3.12/importlib/__init__.py", line 90, in import_module
ERROR 02-17 09:29:32 registry.py:306]     return _bootstrap._gcd_import(name[level:], package, level)
ERROR 02-17 09:29:32 registry.py:306]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 1387, in _gcd_import
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 1360, in _find_and_load
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 1331, in _find_and_load_unlocked
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 935, in _load_unlocked
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap_external>", line 995, in exec_module
ERROR 02-17 09:29:32 registry.py:306]   File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
ERROR 02-17 09:29:32 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 36, in <module>
ERROR 02-17 09:29:32 registry.py:306]     from transformers.models.qwen2_5_vl import (Qwen2_5_VLImageProcessor,
ERROR 02-17 09:29:32 registry.py:306] ImportError: cannot import name 'Qwen2_5_VLImageProcessor' from 'transformers.models.qwen2_5_vl' (/home/itadmin/.local/lib/python3.12/site-packages/transformers/models/qwen2_5_vl/__init__.py). Did you mean: 'Qwen2_5_VLProcessor'?
ERROR 02-17 09:29:32 registry.py:306] 
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/scripts.py", line 210, in <module>
    main()
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/scripts.py", line 204, in main
    args.dispatch_function(args)
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/scripts.py", line 44, in serve
    uvloop.run(run_server(args))
  File "/home/itadmin/.local/lib/python3.12/site-packages/uvloop/__init__.py", line 109, in run
    return __asyncio.run(
           ^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/home/itadmin/.local/lib/python3.12/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
           ^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 875, in run_server
    async with build_async_engine_client(args) as engine_client:
  File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 136, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
  File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 217, in build_async_engine_client_from_engine_args
    engine_config = engine_args.create_engine_config()
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1075, in create_engine_config
    model_config = self.create_model_config()
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 998, in create_model_config
    return ModelConfig(
           ^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 364, in __init__
    self.multimodal_config = self._init_multimodal_config(
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 424, in _init_multimodal_config
    if ModelRegistry.is_multimodal_model(architectures):
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 445, in is_multimodal_model
    model_cls, _ = self.inspect_model_cls(architectures)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 405, in inspect_model_cls
    return self._raise_for_unsupported(architectures)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 357, in _raise_for_unsupported
    raise ValueError(
ValueError: Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.
ERROR 02-17 09:29:36 registry.py:306] Error in inspecting model architecture 'Qwen2_5_VLForConditionalGeneration'
ERROR 02-17 09:29:36 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 507, in _run_in_subprocess
ERROR 02-17 09:29:36 registry.py:306]     returned.check_returncode()
ERROR 02-17 09:29:36 registry.py:306]   File "/usr/lib/python3.12/subprocess.py", line 502, in check_returncode
ERROR 02-17 09:29:36 registry.py:306]     raise CalledProcessError(self.returncode, self.args, self.stdout,
ERROR 02-17 09:29:36 registry.py:306] subprocess.CalledProcessError: Command '['/usr/bin/python3', '-m', 'vllm.model_executor.models.registry']' returned non-zero exit status 1.
ERROR 02-17 09:29:36 registry.py:306] 
ERROR 02-17 09:29:36 registry.py:306] The above exception was the direct cause of the following exception:
ERROR 02-17 09:29:36 registry.py:306] 
ERROR 02-17 09:29:36 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 304, in _try_inspect_model_cls
ERROR 02-17 09:29:36 registry.py:306]     return model.inspect_model_cls()
ERROR 02-17 09:29:36 registry.py:306]            ^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 275, in inspect_model_cls
ERROR 02-17 09:29:36 registry.py:306]     return _run_in_subprocess(
ERROR 02-17 09:29:36 registry.py:306]            ^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 510, in _run_in_subprocess
ERROR 02-17 09:29:36 registry.py:306]     raise RuntimeError(f"Error raised in subprocess:\n"
ERROR 02-17 09:29:36 registry.py:306] RuntimeError: Error raised in subprocess:
ERROR 02-17 09:29:36 registry.py:306] <frozen runpy>:128: 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
ERROR 02-17 09:29:36 registry.py:306] Traceback (most recent call last):
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen runpy>", line 198, in _run_module_as_main
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen runpy>", line 88, in _run_code
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 531, in <module>
ERROR 02-17 09:29:36 registry.py:306]     _run()
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 524, in _run
ERROR 02-17 09:29:36 registry.py:306]     result = fn()
ERROR 02-17 09:29:36 registry.py:306]              ^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 276, in <lambda>
ERROR 02-17 09:29:36 registry.py:306]     lambda: _ModelInfo.from_model_cls(self.load_model_cls()))
ERROR 02-17 09:29:36 registry.py:306]                                       ^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 279, in load_model_cls
ERROR 02-17 09:29:36 registry.py:306]     mod = importlib.import_module(self.module_name)
ERROR 02-17 09:29:36 registry.py:306]           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "/usr/lib/python3.12/importlib/__init__.py", line 90, in import_module
ERROR 02-17 09:29:36 registry.py:306]     return _bootstrap._gcd_import(name[level:], package, level)
ERROR 02-17 09:29:36 registry.py:306]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 1387, in _gcd_import
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 1360, in _find_and_load
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 1331, in _find_and_load_unlocked
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 935, in _load_unlocked
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap_external>", line 995, in exec_module
ERROR 02-17 09:29:36 registry.py:306]   File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
ERROR 02-17 09:29:36 registry.py:306]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 36, in <module>
ERROR 02-17 09:29:36 registry.py:306]     from transformers.models.qwen2_5_vl import (Qwen2_5_VLImageProcessor,
ERROR 02-17 09:29:36 registry.py:306] ImportError: cannot import name 'Qwen2_5_VLImageProcessor' from 'transformers.models.qwen2_5_vl' (/home/itadmin/.local/lib/python3.12/site-packages/transformers/models/qwen2_5_vl/__init__.py). Did you mean: 'Qwen2_5_VLProcessor'?
ERROR 02-17 09:29:36 registry.py:306] 
ERROR 02-17 09:29:36 engine.py:389] Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.
ERROR 02-17 09:29:36 engine.py:389] Traceback (most recent call last):
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 380, in run_mp_engine
ERROR 02-17 09:29:36 engine.py:389]     engine = MQLLMEngine.from_engine_args(engine_args=engine_args,
ERROR 02-17 09:29:36 engine.py:389]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 118, in from_engine_args
ERROR 02-17 09:29:36 engine.py:389]     engine_config = engine_args.create_engine_config(usage_context)
ERROR 02-17 09:29:36 engine.py:389]                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1075, in create_engine_config
ERROR 02-17 09:29:36 engine.py:389]     model_config = self.create_model_config()
ERROR 02-17 09:29:36 engine.py:389]                    ^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 998, in create_model_config
ERROR 02-17 09:29:36 engine.py:389]     return ModelConfig(
ERROR 02-17 09:29:36 engine.py:389]            ^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 364, in __init__
ERROR 02-17 09:29:36 engine.py:389]     self.multimodal_config = self._init_multimodal_config(
ERROR 02-17 09:29:36 engine.py:389]                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 424, in _init_multimodal_config
ERROR 02-17 09:29:36 engine.py:389]     if ModelRegistry.is_multimodal_model(architectures):
ERROR 02-17 09:29:36 engine.py:389]        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 445, in is_multimodal_model
ERROR 02-17 09:29:36 engine.py:389]     model_cls, _ = self.inspect_model_cls(architectures)
ERROR 02-17 09:29:36 engine.py:389]                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 405, in inspect_model_cls
ERROR 02-17 09:29:36 engine.py:389]     return self._raise_for_unsupported(architectures)
ERROR 02-17 09:29:36 engine.py:389]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-17 09:29:36 engine.py:389]   File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 357, in _raise_for_unsupported
ERROR 02-17 09:29:36 engine.py:389]     raise ValueError(
ERROR 02-17 09:29:36 engine.py:389] ValueError: Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.
Process SpawnProcess-1:
Traceback (most recent call last):
  File "/usr/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/usr/lib/python3.12/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 391, in run_mp_engine
    raise e
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 380, in run_mp_engine
    engine = MQLLMEngine.from_engine_args(engine_args=engine_args,
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 118, in from_engine_args
    engine_config = engine_args.create_engine_config(usage_context)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1075, in create_engine_config
    model_config = self.create_model_config()
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 998, in create_model_config
    return ModelConfig(
           ^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 364, in __init__
    self.multimodal_config = self._init_multimodal_config(
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/config.py", line 424, in _init_multimodal_config
    if ModelRegistry.is_multimodal_model(architectures):
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 445, in is_multimodal_model
    model_cls, _ = self.inspect_model_cls(architectures)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 405, in inspect_model_cls
    return self._raise_for_unsupported(architectures)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itadmin/.local/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 357, in _raise_for_unsupported
    raise ValueError(
ValueError: Model architectures ['Qwen2_5_VLForConditionalGeneration'] failed to be inspected. Please check the logs for more details.```

[DarkLight1337]

There is a breaking change in transformers dev. You need to update vLLM to latest dev and also redownload the HF model repo.

[mkvn-1]

Also pip install --force-reinstall git+https://github.com/huggingface/transformers.git@9985d06add07a4cc691dc54a7e34f54205c04d40 solved this issue.

[usun1997]

I get the same issue. I use pip install transformers to get 4.49.0 version and still get the same error. Why is that?