Created
March 20, 2025 15:50
-
-
Save didier-durand/1c2d1b5267b59e4eb11db70ef113a271 to your computer and use it in GitHub Desktop.
Nemotron on SGLANG
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| cheduler hit an exception: Traceback (most recent call last): | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/managers/scheduler.py", line 1748, in run_scheduler_process | |
| scheduler = Scheduler(server_args, port_args, gpu_id, tp_rank, dp_rank) | |
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/managers/scheduler.py", line 218, in __init__ | |
| self.tp_worker = TpWorkerClass( | |
| ^^^^^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/managers/tp_worker_overlap_thread.py", line 63, in __init__ | |
| self.worker = TpModelWorker(server_args, gpu_id, tp_rank, dp_rank, nccl_port) | |
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/managers/tp_worker.py", line 74, in __init__ | |
| self.model_runner = ModelRunner( | |
| ^^^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/model_executor/model_runner.py", line 166, in __init__ | |
| self.initialize(min_per_gpu_memory) | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/model_executor/model_runner.py", line 176, in initialize | |
| self.load_model() | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/model_executor/model_runner.py", line 361, in load_model | |
| self.model = get_model( | |
| ^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/model_loader/__init__.py", line 22, in get_model | |
| return loader.load_model( | |
| ^^^^^^^^^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/model_loader/loader.py", line 358, in load_model | |
| model = _initialize_model( | |
| ^^^^^^^^^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/model_loader/loader.py", line 137, in _initialize_model | |
| model_class, _ = get_model_architecture(model_config) | |
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/model_loader/utils.py", line 37, in get_model_architecture | |
| return ModelRegistry.resolve_model_cls(architectures) | |
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/models/registry.py", line 65, in resolve_model_cls | |
| return self._raise_for_unsupported(architectures) | |
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | |
| File "/usr/local/lib/python3.12/site-packages/sglang/srt/models/registry.py", line 32, in _raise_for_unsupported | |
| raise ValueError( | |
| ValueError: Model architectures ['DeciLMForCausalLM'] are not supported for now. Supported architectures: dict_keys(['BaichuanForCausalLM', 'ChatGLMModel', 'CohereForCausalLM', 'Cohere2ForCausalLM', 'DbrxForCausalLM', 'DeepseekForCausalLM', 'MultiModalityCausalLM', 'DeepseekV3ForCausalLMNextN', 'DeepseekV2ForCausalLM', 'DeepseekV3ForCausalLM', 'ExaoneForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'Gemma2ForSequenceClassification', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GraniteForCausalLM', 'Grok1ForCausalLM', 'Grok1ModelForCausalLM', 'InternLM2ForCausalLM', 'InternLM2ForRewardModel', 'LlamaForCausalLM', 'Phi3ForCausalLM', 'InternLM3ForCausalLM', 'LlamaForClassification', 'LlamaForCausalLMEagle', 'LlamaEmbeddingModel', 'MistralModel', 'LlamaForSequenceClassification', 'LlamaForSequenceClassificationWithNormal_Weights', 'LlavaLlamaForCausalLM', 'LlavaQwenForCausalLM', 'LlavaMistralForCausalLM', 'LlavaVidForCausalLM', 'MiniCPMForCausalLM', 'MiniCPM3ForCausalLM', 'MiniCPMV', 'MistralForCausalLM', 'MixtralForCausalLM', 'QuantMixtralForCausalLM', 'MllamaForConditionalGeneration', 'OlmoForCausalLM', 'Olmo2ForCausalLM', 'OlmoeForCausalLM', 'Phi3SmallForCausalLM', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'Qwen2_5_VLForConditionalGeneration', 'Qwen2ForCausalLMEagle', 'Qwen2MoeForCausalLM', 'Qwen2ForRewardModel', 'Qwen2VLForConditionalGeneration', 'StableLmForCausalLM', 'TorchNativeLlamaForCausalLM', 'TorchNativePhi3ForCausalLM', 'XverseForCausalLM', 'XverseMoeForCausalLM', 'YiVLForCausalLM']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment