Not supported architectures GroveMoeForCausalLM

[1661691223]

I used the sglang official image sglang:v0.4.6.post5-cu124 as the base image build, but couldn't start GroveMoe-Inst. Can give me some advice? Looking forward to receiving a reply

[2025-09-11 11:41:54 TP1] Scheduler hit an exception: Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 2297, in run_scheduler_process
    scheduler = Scheduler(server_args, port_args, gpu_id, tp_rank, pp_rank, dp_rank)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 277, in __init__
    self.tp_worker = TpWorkerClass(
  File "/sgl-workspace/sglang/python/sglang/srt/managers/tp_worker_overlap_thread.py", line 64, in __init__
    self.worker = TpModelWorker(
  File "/sgl-workspace/sglang/python/sglang/srt/managers/tp_worker.py", line 78, in __init__
    self.model_runner = ModelRunner(
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 231, in __init__
    self.initialize(min_per_gpu_memory)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 246, in initialize
    compute_initial_expert_location_metadata(server_args, self.model_config)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/expert_location.py", line 367, in compute_initial_expert_location_metadata
    return ExpertLocationMetadata.init_trivial(server_args, model_config)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/expert_location.py", line 84, in init_trivial
    common = ExpertLocationMetadata._init_common(server_args, model_config)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/expert_location.py", line 162, in _init_common
    ModelConfigForExpertLocation.from_model_config(model_config)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/expert_location.py", line 352, in from_model_config
    model_class, _ = get_model_architecture(model_config)
  File "/sgl-workspace/sglang/python/sglang/srt/model_loader/utils.py", line 37, in get_model_architecture
    return ModelRegistry.resolve_model_cls(architectures)
  File "/sgl-workspace/sglang/python/sglang/srt/models/registry.py", line 65, in resolve_model_cls
    return self._raise_for_unsupported(architectures)
  File "/sgl-workspace/sglang/python/sglang/srt/models/registry.py", line 32, in _raise_for_unsupported
    raise ValueError(
ValueError: Model architectures ['modeling_grove_moe.GroveMoeForCausalLM'] are not supported for now. Supported architectures: dict_keys(['BaichuanForCausalLM', 'BertModel', 'Contriever', 'ChatGLMModel', 'CLIPModel', 'CohereForCausalLM', 'Cohere2ForCausalLM', 'DbrxForCausalLM', 'DeepseekForCausalLM', 'MultiModalityCausalLM', 'DeepseekV3ForCausalLMNextN', 'DeepseekV2ForCausalLM', 'DeepseekV3ForCausalLM', 'DeepseekVL2ForCausalLM', 'ExaoneForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'Gemma2ForSequenceClassification', 'Gemma3ForCausalLM', 'Gemma3ForConditionalGeneration', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GraniteForCausalLM', 'Grok1ForCausalLM', 'Grok1ModelForCausalLM', 'InternLM2ForCausalLM', 'InternLM2ForRewardModel', 'InternVLChatModel', 'KimiVLForConditionalGeneration', 'LlamaForCausalLM', 'Phi3ForCausalLM', 'InternLM3ForCausalLM', 'Llama4ForCausalLM', 'LlamaForClassification', 'LlamaForCausalLMEagle', 'LlamaForCausalLMEagle3', 'LlamaEmbeddingModel', 'MistralModel', 'LlamaForSequenceClassification', 'LlamaForSequenceClassificationWithNormal_Weights', 'LlavaLlamaForCausalLM', 'LlavaQwenForCausalLM', 'LlavaMistralForCausalLM', 'LlavaForConditionalGeneration', 'LlavaVidForCausalLM', 'MiMoForCausalLM', 'MiMoMTP', 'MiniCPMForCausalLM', 'MiniCPM3ForCausalLM', 'MiniCPMO', 'MiniCPMV', 'MistralForCausalLM', 'Mistral3ForConditionalGeneration', 'MixtralForCausalLM', 'QuantMixtralForCausalLM', 'MllamaForConditionalGeneration', 'Llama4ForConditionalGeneration', 'OlmoForCausalLM', 'Olmo2ForCausalLM', 'OlmoeForCausalLM', 'Phi3SmallForCausalLM', 'PixtralVisionModel', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'Qwen2_5_VLForConditionalGeneration', 'Qwen2ForSequenceClassification', 'Qwen2ForCausalLMEagle', 'Qwen2MoeForCausalLM', 'Qwen2ForRewardModel', 'Qwen2VLForConditionalGeneration', 'Qwen3ForCausalLM', 'Qwen3MoeForCausalLM', 'XLMRobertaModel', 'StableLmForCausalLM', 'TorchNativeLlamaForCausalLM', 'TorchNativePhi3ForCausalLM', 'XverseForCausalLM', 'XverseMoeForCausalLM', 'YiVLForCausalLM'])

[2025-09-11 11:41:54] Received sigquit from a child process. It usually means the child failed.

The Dockerfile is as follows：

FROM sglang:v0.4.6.post5-cu124
COPY src/transformers-4.51.3 /root/src/transformers-4.51.3
COPY src/sglang-0.4.6.post5 /root/src/sglang-0.4.6.post5
RUN cd /root/src/transformers-4.51.3 && \
    rm -rf /sgl-workspace/sglang/python/sglang /sgl-workspace/sglang/python/sglang.egg-info/ &&
    pip install . && \
    cd /root/src/sglang-0.4.6.post5 && \
    pip install . --target /sgl-workspace/sglang/python/