moonshotai

/

Kimi-K2.5

like 2.12k

Follow

Moonshot AI 6.78k

(APIServer pid=1241691) INFO 02-05 18:02:35 [api_server.py:1272] vLLM API server version 0.14.1
(APIServer pid=1241691) INFO 02-05 18:02:35 [utils.py:263] non-default args: {'model_tag': '/data/hf-cache/hub/models--moonshotai--Kimi-K2.5/snapshots/6650964d566fe57e540934e575005af04e933bbe', 'tool_call_parser': 'kimi_k2', 'model': '/data/hf-cache/hub/models--moonshotai--Kimi-K2.5/snapshots/6650964d566fe57e540934e575005af04e933bbe', 'trust_remote_code': True, 'reasoning_parser': 'kimi_k2', 'tensor_parallel_size': 8, 'mm_encoder_tp_mode': 'data'}
(APIServer pid=1241691) The argument trust_remote_code is to be used with Auto classes. It has no effect here and is ignored.
(APIServer pid=1241691) The argument trust_remote_code is to be used with Auto classes. It has no effect here and is ignored.
(APIServer pid=1241691) INFO 02-05 18:02:35 [config.py:393] Replacing legacy 'type' key with 'rope_type'
(APIServer pid=1241691) Traceback (most recent call last):
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/bin/vllm", line 10, in
(APIServer pid=1241691) sys.exit(main())
(APIServer pid=1241691) ~~~~^^
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/vllm/entrypoints/cli/main.py", line 73, in main
(APIServer pid=1241691) args.dispatch_function(args)
(APIServer pid=1241691) ~~~~~~~~~~~~~~~~~~~~~~^^^^^^
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/vllm/entrypoints/cli/serve.py", line 60, in cmd
(APIServer pid=1241691) uvloop.run(run_server(args))
(APIServer pid=1241691) ~~~~~~~~~~^^^^^^^^^^^^^^^^^^
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/uvloop/init.py", line 96, in run
(APIServer pid=1241691) return __asyncio.run(
(APIServer pid=1241691) ~~~~~~~~~~~~~^
(APIServer pid=1241691) wrapper(),
(APIServer pid=1241691) ^^^^^^^^^^
(APIServer pid=1241691) ...<2 lines>...
(APIServer pid=1241691) **run_kwargs
(APIServer pid=1241691) ^^^^^^^^^^^^
(APIServer pid=1241691) )
(APIServer pid=1241691) ^
(APIServer pid=1241691) File "/home/user/.local/share/uv/python/cpython-3.13.11-linux-x86_64-gnu/lib/python3.13/asyncio/runners.py", line 195, in run
(APIServer pid=1241691) return runner.run(main)
(APIServer pid=1241691) ~~~~~~~~~~^^^^^^
(APIServer pid=1241691) File "/home/user/.local/share/uv/python/cpython-3.13.11-linux-x86_64-gnu/lib/python3.13/asyncio/runners.py", line 118, in run
(APIServer pid=1241691) return self._loop.run_until_complete(task)
(APIServer pid=1241691) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^
(APIServer pid=1241691) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/uvloop/init.py", line 48, in wrapper
(APIServer pid=1241691) return await main
(APIServer pid=1241691) ^^^^^^^^^^
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/vllm/entrypoints/openai/api_server.py", line 1319, in run_server
(APIServer pid=1241691) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/vllm/entrypoints/openai/api_server.py", line 1338, in run_server_worker
(APIServer pid=1241691) async with build_async_engine_client(
(APIServer pid=1241691) ~~~~~~~~~~~~~~~~~~~~~~~~~^
(APIServer pid=1241691) args,
(APIServer pid=1241691) ^^^^^
(APIServer pid=1241691) client_config=client_config,
(APIServer pid=1241691) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1241691) ) as engine_client:
(APIServer pid=1241691) ^
(APIServer pid=1241691) File "/home/user/.local/share/uv/python/cpython-3.13.11-linux-x86_64-gnu/lib/python3.13/contextlib.py", line 214, in aenter
(APIServer pid=1241691) return await anext(self.gen)
(APIServer pid=1241691) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/vllm/entrypoints/openai/api_server.py", line 173, in build_async_engine_client
(APIServer pid=1241691) async with build_async_engine_client_from_engine_args(
(APIServer pid=1241691) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
(APIServer pid=1241691) engine_args,
(APIServer pid=1241691) ^^^^^^^^^^^^
(APIServer pid=1241691) ...<2 lines>...
(APIServer pid=1241691) client_config=client_config,
(APIServer pid=1241691) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1241691) ) as engine:
(APIServer pid=1241691) ^
(APIServer pid=1241691) File "/home/user/.local/share/uv/python/cpython-3.13.11-linux-x86_64-gnu/lib/python3.13/contextlib.py", line 214, in aenter
(APIServer pid=1241691) return await anext(self.gen)
(APIServer pid=1241691) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/vllm/entrypoints/openai/api_server.py", line 199, in build_async_engine_client_from_engine_args
(APIServer pid=1241691) vllm_config = engine_args.create_engine_config(usage_context=usage_context)
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/vllm/engine/arg_utils.py", line 1369, in create_engine_config
(APIServer pid=1241691) model_config = self.create_model_config()
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/vllm/engine/arg_utils.py", line 1223, in create_model_config
(APIServer pid=1241691) return ModelConfig(
(APIServer pid=1241691) model=self.model,
(APIServer pid=1241691) ...<49 lines>...
(APIServer pid=1241691) io_processor_plugin=self.io_processor_plugin,
(APIServer pid=1241691) )
(APIServer pid=1241691) File "/home/user/lin/AI-Research/.venv/lib/python3.13/site-packages/pydantic/_internal/_dataclasses.py", line 121, in init
(APIServer pid=1241691) s.pydantic_validator.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
(APIServer pid=1241691) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1241691) pydantic_core._pydantic_core.ValidationError: 1 validation error for ModelConfig
(APIServer pid=1241691) Value error, Model architectures ['KimiK25ForConditionalGeneration'] are not supported for now. Supported architectures: dict_keys(['AfmoeForCausalLM', 'ApertusForCausalLM', 'AquilaModel', 'AquilaForCausalLM', 'ArceeForCausalLM', 'ArcticForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM', 'BailingMoeForCausalLM', 'BailingMoeV2ForCausalLM', 'BambaForCausalLM', 'BloomForCausalLM', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'CohereForCausalLM', 'Cohere2ForCausalLM', 'CwmForCausalLM', 'DbrxForCausalLM', 'DeciLMForCausalLM', 'DeepseekForCausalLM', 'DeepseekV2ForCausalLM', 'DeepseekV3ForCausalLM', 'DeepseekV32ForCausalLM', 'Dots1ForCausalLM', 'Ernie4_5ForCausalLM', 'Ernie4_5_MoeForCausalLM', 'ExaoneForCausalLM', 'Exaone4ForCausalLM', 'ExaoneMoEForCausalLM', 'Fairseq2LlamaForCausalLM', 'FalconForCausalLM', 'FalconMambaForCausalLM', 'FalconH1ForCausalLM', 'FlexOlmoForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'Gemma3ForCausalLM', 'Gemma3nForCausalLM', 'Qwen3NextForCausalLM', 'GlmForCausalLM', 'Glm4ForCausalLM', 'Glm4MoeForCausalLM', 'GptOssForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GPTJForCausalLM', 'GPTNeoXForCausalLM', 'GraniteForCausalLM', 'GraniteMoeForCausalLM', 'GraniteMoeHybridForCausalLM', 'GraniteMoeSharedForCausalLM', 'GritLM', 'Grok1ModelForCausalLM', 'Grok1ForCausalLM', 'HunYuanMoEV1ForCausalLM', 'HunYuanDenseV1ForCausalLM', 'HCXVisionForCausalLM', 'InternLMForCausalLM', 'InternLM2ForCausalLM', 'InternLM2VEForCausalLM', 'InternLM3ForCausalLM', 'IQuestCoderForCausalLM', 'IQuestLoopCoderForCausalLM', 'JAISLMHeadModel', 'Jais2ForCausalLM', 'JambaForCausalLM', 'KimiLinearForCausalLM', 'Lfm2ForCausalLM', 'Lfm2MoeForCausalLM', 'LlamaForCausalLM', 'Llama4ForCausalLM', 'LLaMAForCausalLM', 'LongcatFlashForCausalLM', 'MambaForCausalLM', 'Mamba2ForCausalLM', 'MiniCPMForCausalLM', 'MiniCPM3ForCausalLM', 'MiniMaxForCausalLM', 'MiniMaxText01ForCausalLM', 'MiniMaxM1ForCausalLM', 'MiniMaxM2ForCausalLM', 'MistralForCausalLM', 'MistralLarge3ForCausalLM', 'MixtralForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'MiMoForCausalLM', 'MiMoV2FlashForCausalLM', 'NemotronForCausalLM', 'NemotronHForCausalLM', 'OlmoForCausalLM', 'Olmo2ForCausalLM', 'Olmo3ForCausalLM', 'OlmoeForCausalLM', 'OPTForCausalLM', 'OrionForCausalLM', 'OuroForCausalLM', 'PanguEmbeddedForCausalLM', 'PanguProMoEV2ForCausalLM', 'PanguUltraMoEForCausalLM', 'PersimmonForCausalLM', 'PhiForCausalLM', 'Phi3ForCausalLM', 'PhiMoEForCausalLM', 'Plamo2ForCausalLM', 'Plamo3ForCausalLM', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'Qwen3ForCausalLM', 'Qwen3MoeForCausalLM', 'RWForCausalLM', 'SeedOssForCausalLM', 'Step3TextForCausalLM', 'StableLMEpochForCausalLM', 'StableLmForCausalLM', 'Starcoder2ForCausalLM', 'SolarForCausalLM', 'TeleChatForCausalLM', 'TeleChat2ForCausalLM', 'TeleFLMForCausalLM', 'XverseForCausalLM', 'Zamba2ForCausalLM', 'BertModel', 'BertSpladeSparseEmbeddingModel', 'Gemma2Model', 'Gemma3TextModel', 'GPT2ForSequenceClassification', 'GteModel', 'GteNewModel', 'InternLM2ForRewardModel', 'JambaForSequenceClassification', 'LlamaBidirectionalModel', 'LlamaModel', 'MistralModel', 'ModernBertModel', 'NomicBertModel', 'Qwen2Model', 'Qwen2ForRewardModel', 'Qwen2ForProcessRewardModel', 'RobertaForMaskedLM', 'RobertaModel', 'XLMRobertaModel', 'CLIPModel', 'LlavaNextForConditionalGeneration', 'Phi3VForCausalLM', 'Qwen2VLForConditionalGeneration', 'SiglipModel', 'PrithviGeoSpatialMAE', 'Terratorch', 'BertForSequenceClassification', 'BertForTokenClassification', 'GteNewForSequenceClassification', 'JinaVLForRanking', 'LlamaBidirectionalForSequenceClassification', 'ModernBertForSequenceClassification', 'ModernBertForTokenClassification', 'RobertaForSequenceClassification', 'XLMRobertaForSequenceClassification', 'AriaForConditionalGeneration', 'AudioFlamingo3ForConditionalGeneration', 'AyaVisionForConditionalGeneration', 'BagelForConditionalGeneration', 'BeeForConditionalGeneration', 'Blip2ForConditionalGeneration', 'ChameleonForConditionalGeneration', 'Cohere2VisionForConditionalGeneration', 'DeepseekVLV2ForCausalLM', 'DeepseekOCRForCausalLM', 'DotsOCRForCausalLM', 'Ernie4_5_VLMoeForConditionalGeneration', 'FuyuForCausalLM', 'Gemma3ForConditionalGeneration', 'Gemma3nForConditionalGeneration', 'GlmAsrForConditionalGeneration', 'GLM4VForCausalLM', 'Glm4vForConditionalGeneration', 'Glm4vMoeForConditionalGeneration', 'GraniteSpeechForConditionalGeneration', 'H2OVLChatModel', 'HunYuanVLForConditionalGeneration', 'InternVLChatModel', 'NemotronH_Nano_VL_V2', 'OpenCUAForConditionalGeneration', 'InternS1ForConditionalGeneration', 'InternVLForConditionalGeneration', 'Idefics3ForConditionalGeneration', 'IsaacForConditionalGeneration', 'SmolVLMForConditionalGeneration', 'KananaVForConditionalGeneration', 'KeyeForConditionalGeneration', 'KeyeVL1_5ForConditionalGeneration', 'RForConditionalGeneration', 'KimiVLForConditionalGeneration', 'LightOnOCRForConditionalGeneration', 'Lfm2VlForConditionalGeneration', 'Llama_Nemotron_Nano_VL', 'Llama4ForConditionalGeneration', 'LlavaForConditionalGeneration', 'LlavaNextVideoForConditionalGeneration', 'LlavaOnevisionForConditionalGeneration', 'MantisForConditionalGeneration', 'MiDashengLMModel', 'MiniMaxVL01ForConditionalGeneration', 'MiniCPMO', 'MiniCPMV', 'Mistral3ForConditionalGeneration', 'MolmoForCausalLM', 'NVLM_D', 'Ovis', 'Ovis2_5', 'PaddleOCRVLForConditionalGeneration', 'PaliGemmaForConditionalGeneration', 'Phi4MMForCausalLM', 'PixtralForConditionalGeneration', 'QwenVLForConditionalGeneration', 'Qwen2_5_VLForConditionalGeneration', 'Qwen2AudioForConditionalGeneration', 'Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration', 'Qwen3OmniMoeForConditionalGeneration', 'Qwen3VLForConditionalGeneration', 'Qwen3VLMoeForConditionalGeneration', 'SkyworkR1VChatModel', 'Step3VLForConditionalGeneration', 'TarsierForConditionalGeneration', 'Tarsier2ForConditionalGeneration', 'UltravoxModel', 'VoxtralForConditionalGeneration', 'VoxtralStreamingGeneration', 'NemotronParseForConditionalGeneration', 'WhisperForConditionalGeneration', 'MiMoMTPModel', 'EagleLlamaForCausalLM', 'EagleLlama4ForCausalLM', 'EagleMiniCPMForCausalLM', 'Eagle3LlamaForCausalLM', 'LlamaForCausalLMEagle3', 'Eagle3Qwen2_5vlForCausalLM', 'Eagle3Qwen3vlForCausalLM', 'EagleMistralLarge3ForCausalLM', 'EagleDeepSeekMTPModel', 'DeepSeekMTPModel', 'ErnieMTPModel', 'ExaoneMoeMTP', 'LongCatFlashMTPModel', 'Glm4MoeMTPModel', 'MedusaModel', 'OpenPanguMTPModel', 'Qwen3NextMTP', 'SmolLM3ForCausalLM', 'Emu3ForConditionalGeneration', 'TransformersForCausalLM', 'TransformersMoEForCausalLM', 'TransformersMultiModalForCausalLM', 'TransformersMultiModalMoEForCausalLM', 'TransformersEmbeddingModel', 'TransformersMoEEmbeddingModel', 'TransformersMultiModalEmbeddingModel', 'TransformersForSequenceClassification', 'TransformersMoEForSequenceClassification', 'TransformersMultiModalForSequenceClassification']) [type=value_error, input_value=ArgsKwargs((), {'model': ...rocessor_plugin': None}), input_type=ArgsKwargs]
(APIServer pid=1241691) For further information visit https://errors.pydantic.dev/2.12/v/value_error