vLLM not support GPTNeoForCausalLM architecture
Traceback (most recent call last):
File "/data/miniconda3/lib/python3.9/runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/data/miniconda3/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/data/vllm_repo/vllm/entrypoints/api_server.py", line 90, in
engine = AsyncLLMEngine.from_engine_args(engine_args)
File "/data/vllm_repo/vllm/engine/async_llm_engine.py", line 625, in from_engine_args
engine = cls(parallel_config.worker_use_ray,
File "/data/vllm_repo/vllm/engine/async_llm_engine.py", line 321, in init
self.engine = self._init_engine(*args, **kwargs)
File "/data/vllm_repo/vllm/engine/async_llm_engine.py", line 366, in _init_engine
return engine_class(*args, **kwargs)
File "/data/vllm_repo/vllm/engine/llm_engine.py", line 120, in init
self._init_workers()
File "/data/vllm_repo/vllm/engine/llm_engine.py", line 164, in _init_workers
self._run_workers("load_model")
File "/data/vllm_repo/vllm/engine/llm_engine.py", line 1006, in _run_workers
driver_worker_output = getattr(self.driver_worker,
File "/data/vllm_repo/vllm/worker/worker.py", line 102, in load_model
self.model_runner.load_model()
File "/data/vllm_repo/vllm/worker/model_runner.py", line 84, in load_model
self.model = get_model(self.model_config, self.device_config,
File "/data/vllm_repo/vllm/model_executor/model_loader.py", line 43, in get_model
model_class = _get_model_architecture(model_config)
File "/data/vllm_repo/vllm/model_executor/model_loader.py", line 35, in _get_model_architecture
raise ValueError(
ValueError: Model architectures ['GPTNeoForCausalLM'] are not supported for now. Supported architectures: ['AquilaModel', 'AquilaForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM', 'BloomForCausalLM', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'DeciLMForCausalLM', 'DeepseekForCausalLM', 'FalconForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GPTJForCausalLM', 'GPTNeoXForCausalLM', 'InternLMForCausalLM', 'InternLM2ForCausalLM', 'LlamaForCausalLM', 'LLaMAForCausalLM', 'MistralForCausalLM', 'MixtralForCausalLM', 'QuantMixtralForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'OPTForCausalLM', 'PhiForCausalLM', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'RWForCausalLM', 'StableLMEpochForCausalLM']