Missing Qwen3.5MoeForConditionalGeneration support

```
pip install --upgrade transformers

VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 \
VLLM_WORKER_MULTIPROC_METHOD=spawn \
vllm serve /llm/models/Qwen3.6-35B-A3B-int4-AutoRound \
--port 8000 \
--tensor-parallel-size 2 \
--max-model-len 32768 \
--reasoning-parser qwen3 \
--served-model-name Qwen3.6-35B-A3B-int4 \
--dtype float16 \
--enforce-eager \
--host 0.0.0.0 \
--trust-remote-code \
--disable-sliding-window \
--gpu-memory-utilization 0.9 \
--max-num-batched-tokens 8192 \
--disable-log-requests \
--block-size 16 \
2>&1 | tee /llm/vllm.log

```

[W419 19:48:19.525379168 OperatorEntry.cpp:218] Warning: Warning only once for all operators, other operators may also be overridden.
Overriding a previously registered kernel for the same operator and the same dispatch key
operator: aten::geometric_(Tensor(a!) self, float p, *, Generator? generator=None) -> Tensor(a!)
registered at /pytorch/build/aten/src/ATen/RegisterSchema.cpp:6
dispatch key: XPU
previous kernel: registered at /pytorch/aten/src/ATen/VmapModeRegistrations.cpp:37
new kernel: registered at /root/workspace/frameworks.ai.pytorch.ipex-gpu/build/Release/csrc/gpu/csrc/gpu/xpu/ATen/RegisterXPU_0.cpp:172 (function operator())
INFO 04-19 19:48:22 [scheduler.py:216] Chunked prefill is enabled with max_num_batched_tokens=2048.
WARNING 04-19 19:48:22 [logger.py:133] argument '--disable-log-requests' is deprecated and replaced with '--enable-log-requests'. This will be removed in v0.12.0.
(APIServer pid=1527) INFO 04-19 19:48:22 [api_server.py:1977] vLLM API server version 0.11.2.dev0+g439368496.d20260115
(APIServer pid=1527) INFO 04-19 19:48:22 [utils.py:253] non-default args: {'model_tag': '/llm/models/Qwen3.6-35B-A3B-int4-AutoRound', 'host': '0.0.0.0', 'model': '/llm/models/Qwen3.6-35B-A3B-int4-AutoRound', 'trust_remote_code': True, 'dtype': 'float16', 'max_model_len': 32768, 'enforce_eager': True, 'disable_sliding_window': True, 'served_model_name': ['Qwen3.6-35B-A3B-int4'], 'reasoning_parser': 'qwen3', 'tensor_parallel_size': 2, 'block_size': 16, 'max_num_batched_tokens': 8192}
(APIServer pid=1527) The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
(APIServer pid=1527) Traceback (most recent call last):
(APIServer pid=1527) File "/usr/local/bin/vllm", line 8, in
(APIServer pid=1527) sys.exit(main())
(APIServer pid=1527) ^^^^^^
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/main.py", line 73, in main
(APIServer pid=1527) args.dispatch_function(args)
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/serve.py", line 60, in cmd
(APIServer pid=1527) uvloop.run(run_server(args))
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 96, in run
(APIServer pid=1527) return __asyncio.run(
(APIServer pid=1527) ^^^^^^^^^^^^^^
(APIServer pid=1527) File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
(APIServer pid=1527) return runner.run(main)
(APIServer pid=1527) ^^^^^^^^^^^^^^^^
(APIServer pid=1527) File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
(APIServer pid=1527) return self._loop.run_until_complete(task)
(APIServer pid=1527) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1527) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 48, in wrapper
(APIServer pid=1527) return await main
(APIServer pid=1527) ^^^^^^^^^^
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 2024, in run_server
(APIServer pid=1527) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 2043, in run_server_worker
(APIServer pid=1527) async with build_async_engine_client(
(APIServer pid=1527) File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
(APIServer pid=1527) return await anext(self.gen)
(APIServer pid=1527) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 195, in build_async_engine_client
(APIServer pid=1527) async with build_async_engine_client_from_engine_args(
(APIServer pid=1527) File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
(APIServer pid=1527) return await anext(self.gen)
(APIServer pid=1527) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 221, in build_async_engine_client_from_engine_args
(APIServer pid=1527) vllm_config = engine_args.create_engine_config(usage_context=usage_context)
(APIServer pid=1527) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 1360, in create_engine_config
(APIServer pid=1527) model_config = self.create_model_config()
(APIServer pid=1527) ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 1215, in create_model_config
(APIServer pid=1527) return ModelConfig(
(APIServer pid=1527) ^^^^^^^^^^^^
(APIServer pid=1527) File "/usr/local/lib/python3.12/dist-packages/pydantic/_internal/_dataclasses.py", line 121, in __init__
(APIServer pid=1527) s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
(APIServer pid=1527) pydantic_core._pydantic_core.ValidationError: 1 validation error for ModelConfig
(APIServer pid=1527) Value error, Model architectures ['Qwen3_5MoeForConditionalGeneration'] 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', 'Fairseq2LlamaForCausalLM', 'FalconForCausalLM', 'FalconMambaForCausalLM', 'FalconH1ForCausalLM', 'FlexOlmoForCausalLM', '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', 'KimiLinearForCausalLM', 'Lfm2ForCausalLM', 'Lfm2MoeForCausalLM', 'LlamaForCausalLM', 'Llama4ForCausalLM', 'LLaMAForCausalLM', 'LongcatFlashForCausalLM', 'MambaForCausalLM', 'Mamba2ForCausalLM', 'MiniCPMForCausalLM', 'MiniCPM3ForCausalLM', 'MiniMaxForCausalLM', 'MiniMaxText01ForCausalLM', 'MiniMaxM1ForCausalLM', 'MiniMaxM2ForCausalLM', 'MistralForCausalLM', 'MixtralForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'MiMoForCausalLM', 'NemotronForCausalLM', 'NemotronHForCausalLM', 'OlmoForCausalLM', 'Olmo2ForCausalLM', 'Olmo3ForCausalLM', 'OlmoeForCausalLM', 'OPTForCausalLM', 'OrionForCausalLM', 'OuroForCausalLM', 'PanguEmbeddedForCausalLM', 'PanguUltraMoEForCausalLM', 'PersimmonForCausalLM', 'PhiForCausalLM', 'Phi3ForCausalLM', 'PhiMoEForCausalLM', 'Plamo2ForCausalLM', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'Qwen3ForCausalLM', 'Qwen3MoeForCausalLM', 'RWForCausalLM', 'SeedOssForCausalLM', 'Step3TextForCausalLM', 'StableLMEpochForCausalLM', 'StableLmForCausalLM', 'Starcoder2ForCausalLM', 'SolarForCausalLM', 'TeleChat2ForCausalLM', 'TeleChatForCausalLM', 'TeleFLMForCausalLM', 'XverseForCausalLM', 'Zamba2ForCausalLM', 'BertModel', 'BertSpladeSparseEmbeddingModel', 'Gemma2Model', 'Gemma3TextModel', 'GPT2ForSequenceClassification', 'GteModel', 'GteNewModel', 'InternLM2ForRewardModel', 'JambaForSequenceClassification', 'LlamaModel', 'MistralModel', 'ModernBertModel', 'NomicBertModel', 'Qwen2Model', 'Qwen2ForRewardModel', 'Qwen2ForProcessRewardModel', 'RobertaForMaskedLM', 'RobertaModel', 'XLMRobertaModel', 'CLIPModel', 'LlavaNextForConditionalGeneration', 'Phi3VForCausalLM', 'Qwen2VLForConditionalGeneration', 'SiglipModel', 'PrithviGeoSpatialMAE', 'Terratorch', 'BertForSequenceClassification', 'BertForTokenClassification', 'GteNewForSequenceClassification', 'ModernBertForSequenceClassification', 'ModernBertForTokenClassification', 'RobertaForSequenceClassification', 'XLMRobertaForSequenceClassification', 'JinaVLForRanking', 'AriaForConditionalGeneration', 'AyaVisionForConditionalGeneration', 'BeeForConditionalGeneration', 'Blip2ForConditionalGeneration', 'ChameleonForConditionalGeneration', 'Cohere2VisionForConditionalGeneration', 'DeepseekVLV2ForCausalLM', 'DeepseekOCRForCausalLM', 'DotsOCRForCausalLM', 'Ernie4_5_VLMoeForConditionalGeneration', 'FuyuForCausalLM', 'Gemma3ForConditionalGeneration', 'Gemma3nForConditionalGeneration', 'GLM4VForCausalLM', 'Glm4vForConditionalGeneration', 'Glm4vMoeForConditionalGeneration', 'GraniteSpeechForConditionalGeneration', 'H2OVLChatModel', 'InternVLChatModel', 'NemotronH_Nano_VL_V2', 'InternS1ForConditionalGeneration', 'InternVLForConditionalGeneration', 'Idefics3ForConditionalGeneration', 'SmolVLMForConditionalGeneration', 'KeyeForConditionalGeneration', 'KeyeVL1_5ForConditionalGeneration', 'RForConditionalGeneration', 'KimiVLForConditionalGeneration', 'LightOnOCRForConditionalGeneration', 'Llama_Nemotron_Nano_VL', 'Llama4ForConditionalGeneration', 'LlavaForConditionalGeneration', 'LlavaNextVideoForConditionalGeneration', 'LlavaOnevisionForConditionalGeneration', 'MantisForConditionalGeneration', 'MiDashengLMModel', 'MiniMaxVL01ForConditionalGeneration', 'MiniCPMO', 'MiniCPMV', 'Mistral3ForConditionalGeneration', 'MolmoForCausalLM', 'NVLM_D', 'Ovis', 'Ovis2_5', 'PaddleOCRVLForConditionalGeneration', 'PaliGemmaForConditionalGeneration', 'Phi4MMForCausalLM', 'Phi4MultimodalForCausalLM', 'PixtralForConditionalGeneration', 'QwenVLForConditionalGeneration', 'Qwen2_5_VLForConditionalGeneration', 'Qwen2AudioForConditionalGeneration', 'Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration', 'Qwen3OmniMoeForConditionalGeneration', 'Qwen3VLForConditionalGeneration', 'Qwen3VLMoeForConditionalGeneration', 'SkyworkR1VChatModel', 'Step3VLForConditionalGeneration', 'TarsierForConditionalGeneration', 'Tarsier2ForConditionalGeneration', 'UltravoxModel', 'VoxtralForConditionalGeneration', 'WhisperForConditionalGeneration', 'MiMoMTPModel', 'EagleLlamaForCausalLM', 'EagleLlama4ForCausalLM', 'EagleMiniCPMForCausalLM', 'Eagle3LlamaForCausalLM', 'LlamaForCausalLMEagle3', 'Eagle3Qwen2_5vlForCausalLM', 'EagleDeepSeekMTPModel', 'DeepSeekMTPModel', 'ErnieMTPModel', '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=1527) For further information visit https://errors.pydantic.dev/2.12/v/value_error