[Usage]: vllm 可以部署grounding-dino模型吗

[zkailinzhang]

部署脚本
TOKENIZERS_PARALLELISM=true CUDA_VISIBLE_DEVICES=4 nohup vllm serve /appdata//models/IDEA-Research/grounding-dino-base
--served-model-name dino
--tensor-parallel-size 1
--gpu-memory-utilization 0.9
--port 8002
--host 0.0.0.0

vllm_serve_dino.log 2>&1 &

36m(APIServer pid=3254242)�[0;0m INFO 03-04 09:49:44 [api_server.py:1896] vLLM API server version 0.10.2
�[1;36m(APIServer pid=3254242)�[0;0m INFO 03-04 09:49:44 [utils.py:328] non-default args: {'model_tag': '/appdata/zhangkailin/models/IDEA-Research/grounding-dino-base', 'host': '0.0.0.0', 'port': 8002, 'model': '/appdata/zhangkailin/models/IDEA-Research/grounding-dino-base', 'served_model_name': ['dino']}
�[1;36m(APIServer pid=3254242)�[0;0m Traceback (most recent call last):
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/bin/vllm", line 7, in <module>
�[1;36m(APIServer pid=3254242)�[0;0m     sys.exit(main())
�[1;36m(APIServer pid=3254242)�[0;0m              ^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 54, in main
�[1;36m(APIServer pid=3254242)�[0;0m     args.dispatch_function(args)
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 50, in cmd
�[1;36m(APIServer pid=3254242)�[0;0m     uvloop.run(run_server(args))
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/site-packages/uvloop/__init__.py", line 109, in run
�[1;36m(APIServer pid=3254242)�[0;0m     return __asyncio.run(
�[1;36m(APIServer pid=3254242)�[0;0m            ^^^^^^^^^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home/zhangkailin/.conda/envs/vllm/lib/python3.12/asyncio/runners.py", line 194, in run
�[1;36m(APIServer pid=3254242)�[0;0m     return runner.run(main)
�[1;36m(APIServer pid=3254242)�[0;0m            ^^^^^^^^^^^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home/zhangkailin/.conda/envs/vllm/lib/python3.12/asyncio/runners.py", line 118, in run
�[1;36m(APIServer pid=3254242)�[0;0m     return self._loop.run_until_complete(task)
�[1;36m(APIServer pid=3254242)�[0;0m            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/site-packages/uvloop/__init__.py", line 61, in wrapper
�[1;36m(APIServer pid=3254242)�[0;0m     return await main
�[1;36m(APIServer pid=3254242)�[0;0m            ^^^^^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 1941, in run_server
�[1;36m(APIServer pid=3254242)�[0;0m     await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home/zhangkailin/.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 1961, in run_server_worker
�[1;36m(APIServer pid=3254242)�[0;0m     async with build_async_engine_client(
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/contextlib.py", line 204, in __aenter__
�[1;36m(APIServer pid=3254242)�[0;0m     return await anext(self.gen)
�[1;36m(APIServer pid=3254242)�[0;0m            ^^^^^^^^^^^^^^^^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 179, in build_async_engine_client
�[1;36m(APIServer pid=3254242)�[0;0m     async with build_async_engine_client_from_engine_args(
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/contextlib.py", line 204, in __aenter__
�[1;36m(APIServer pid=3254242)�[0;0m     return await anext(self.gen)
�[1;36m(APIServer pid=3254242)�[0;0m            ^^^^^^^^^^^^^^^^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home/zhangkailin/.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 205, in build_async_engine_client_from_engine_args
�[1;36m(APIServer pid=3254242)�[0;0m     vllm_config = engine_args.create_engine_config(usage_context=usage_context)
�[1;36m(APIServer pid=3254242)�[0;0m                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1119, in create_engine_config
�[1;36m(APIServer pid=3254242)�[0;0m     model_config = self.create_model_config()
�[1;36m(APIServer pid=3254242)�[0;0m                    ^^^^^^^^^^^^^^^^^^^^^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 963, in create_model_config
�[1;36m(APIServer pid=3254242)�[0;0m     return ModelConfig(
�[1;36m(APIServer pid=3254242)�[0;0m            ^^^^^^^^^^^^
�[1;36m(APIServer pid=3254242)�[0;0m   File "/home//.conda/envs/vllm/lib/python3.12/site-packages/pydantic/_internal/_dataclasses.py", line 123, in __init__
�[1;36m(APIServer pid=3254242)�[0;0m     s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
�[1;36m(APIServer pid=3254242)�[0;0m pydantic_core._pydantic_core.ValidationError: 1 validation error for ModelConfig
�[1;36m(APIServer pid=3254242)�[0;0m   Value error, Model architectures ['GroundingDinoForObjectDetection'] are not supported for now. Supported architectures: dict_keys(['ApertusForCausalLM', 'AquilaModel', 'AquilaForCausalLM', 'ArceeForCausalLM', 'ArcticForCausalLM', 'MiniMaxForCausalLM', 'MiniMaxText01ForCausalLM', 'MiniMaxM1ForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM', 'BailingMoeForCausalLM', 'BambaForCausalLM', 'BloomForCausalLM', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'CohereForCausalLM', 'Cohere2ForCausalLM', 'DbrxForCausalLM', 'DeciLMForCausalLM', 'DeepseekForCausalLM', 'DeepseekV2ForCausalLM', 'DeepseekV3ForCausalLM', 'Dots1ForCausalLM', 'Ernie4_5ForCausalLM', 'Ernie4_5_MoeForCausalLM', 'ExaoneForCausalLM', 'Exaone4ForCausalLM', 'FalconForCausalLM', 'Fairseq2LlamaForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'Gemma3ForCausalLM', 'Gemma3nForCausalLM', 'Qwen3NextForCausalLM', 'GlmForCausalLM', 'Glm4ForCausalLM', 'Glm4MoeForCausalLM', 'GptOssForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GPTJForCausalLM', 'GPTNeoXForCausalLM', 'GraniteForCausalLM', 'GraniteMoeForCausalLM', 'GraniteMoeHybridForCausalLM', 'GraniteMoeSharedForCausalLM', 'GritLM', 'Grok1ModelForCausalLM', 'HunYuanMoEV1ForCausalLM', 'HunYuanDenseV1ForCausalLM', 'HCXVisionForCausalLM', 'InternLMForCausalLM', 'InternLM2ForCausalLM', 'InternLM2VEForCausalLM', 'InternLM3ForCausalLM', 'JAISLMHeadModel', 'JambaForCausalLM', 'Lfm2ForCausalLM', 'LlamaForCausalLM', 'Llama4ForCausalLM', 'LLaMAForCausalLM', 'MambaForCausalLM', 'FalconMambaForCausalLM', 'FalconH1ForCausalLM', 'Mamba2ForCausalLM', 'MiniCPMForCausalLM', 'MiniCPM3ForCausalLM', 'MistralForCausalLM', 'MixtralForCausalLM', 'MotifForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'MiMoForCausalLM', 'NemotronForCausalLM', 'NemotronHForCausalLM', 'OlmoForCausalLM', 'Olmo2ForCausalLM', 'OlmoeForCausalLM', 'OPTForCausalLM', 'OrionForCausalLM', 'PersimmonForCausalLM', 'PhiForCausalLM', 'Phi3ForCausalLM', 'PhiMoEForCausalLM', 'Phi4FlashForCausalLM', 'Plamo2ForCausalLM', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'Qwen3ForCausalLM', 'Qwen3MoeForCausalLM', 'RWForCausalLM', 'SeedOssForCausalLM', 'Step3TextForCausalLM', 'StableLMEpochForCausalLM', 'StableLmForCausalLM', 'Starcoder2ForCausalLM', 'SolarForCausalLM', 'TeleChat2ForCausalLM', 'TeleFLMForCausalLM', 'XverseForCausalLM', 'Zamba2ForCausalLM', 'BartModel', 'BartForConditionalGeneration', 'MBartForConditionalGeneration', 'BertModel', 'Gemma2Model', 'Gemma3TextModel', 'GPT2ForSequenceClassification', 'GteModel', 'GteNewModel', 'InternLM2ForRewardModel', 'JambaForSequenceClassification', 'LlamaModel', 'MistralModel', 'ModernBertModel', 'NomicBertModel', 'Qwen2Model', 'Qwen2ForRewardModel', 'Qwen2ForProcessRewardModel', 'RobertaForMaskedLM', 'RobertaModel', 'XLMRobertaModel', 'LlavaNextForConditionalGeneration', 'Phi3VForCausalLM', 'Qwen2VLForConditionalGeneration', 'PrithviGeoSpatialMAE', 'Terratorch', 'BertForSequenceClassification', 'GteNewForSequenceClassification', 'ModernBertForSequenceClassification', 'RobertaForSequenceClassification', 'XLMRobertaForSequenceClassification', 'JinaVLForRanking', 'AriaForConditionalGeneration', 'AyaVisionForConditionalGeneration', 'Blip2ForConditionalGeneration', 'ChameleonForConditionalGeneration', 'Cohere2VisionForConditionalGeneration', 'DeepseekVLV2ForCausalLM', 'Ernie4_5_VLMoeForConditionalGeneration', 'FuyuForCausalLM', 'Gemma3ForConditionalGeneration', 'Gemma3nForConditionalGeneration', 'GLM4VForCausalLM', 'Glm4vForConditionalGeneration', 'Glm4vMoeForConditionalGeneration', 'GraniteSpeechForConditionalGeneration', 'H2OVLChatModel', 'InternVLChatModel', 'NemotronH_Nano_VL', 'InternS1ForConditionalGeneration', 'InternVLForConditionalGeneration', 'Idefics3ForConditionalGeneration', 'SmolVLMForConditionalGeneration', 'KeyeForConditionalGeneration', 'KeyeVL1_5ForConditionalGeneration', 'RForConditionalGeneration', 'KimiVLForConditionalGeneration', 'Llama_Nemotron_Nano_VL', 'LlavaForConditionalGeneration', 'LlavaNextVideoForConditionalGeneration', 'LlavaOnevisionForConditionalGeneration', 'MantisForConditionalGeneration', 'MiDashengLMModel', 'MiniMaxVL01ForConditionalGeneration', 'MiniCPMO', 'MiniCPMV', 'Mistral3ForConditionalGeneration', 'MolmoForCausalLM', 'NVLM_D', 'Ovis', 'Ovis2_5', 'PaliGemmaForConditionalGeneration', 'Phi4MMForCausalLM', 'Phi4MultimodalForCausalLM', 'PixtralForConditionalGeneration', 'QwenVLForConditionalGeneration', 'Qwen2_5_VLForConditionalGeneration', 'Qwen2AudioForConditionalGeneration', 'Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration', 'UltravoxModel', 'Step3VLForConditionalGeneration', 'TarsierForConditionalGeneration', 'Tarsier2ForConditionalGeneration', 'VoxtralForConditionalGeneration', 'DonutForConditionalGeneration', 'Florence2ForConditionalGeneration', 'MllamaForConditionalGeneration', 'Llama4ForConditionalGeneration', 'SkyworkR1VChatModel', 'WhisperForConditionalGeneration', 'MiMoMTPModel', 'EagleLlamaForCausalLM', 'EagleLlama4ForCausalLM', 'EagleMiniCPMForCausalLM', 'Eagle3LlamaForCausalLM', 'LlamaForCausalLMEagle3', 'EagleDeepSeekMTPModel', 'DeepSeekMTPModel', 'ErnieMTPModel', 'Glm4MoeMTPModel', 'MedusaModel', 'Qwen3NextMTP', 'SmolLM3ForCausalLM', 'Emu3ForConditionalGeneration', 'TransformersModel', 'TransformersForCausalLM', 'TransformersForMultimodalLM']) [type=value_error, input_value=ArgsKwargs((), {'model': ...rocessor_plugin': None}), input_type=ArgsKwargs]
�[1;36m(APIServer pid=3254242)�[0;0m     For further information visit https://errors.pydantic.dev/2.11/v/value_error