KeyError: 'model.layers.0.self_attn.k_proj.weight'

[Minami-su]

CUDA_VISIBLE_DEVICES=1 python -m vllm.entrypoints.openai.api_server --model /data/haolu/ckpt/Qwen1.5-32B-Chat_2bit_quip --trust-remote-code --port 8001 --host localhost --dtype half --max-model-len 8000

Traceback (most recent call last):
File "/data/anaconda3/envs/haolu2/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/data/anaconda3/envs/haolu2/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/entrypoints/openai/api_server.py", line 156, in
engine = AsyncLLMEngine.from_engine_args(engine_args)
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/engine/async_llm_engine.py", line 344, in from_engine_args
engine = cls(parallel_config.worker_use_ray,
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/engine/async_llm_engine.py", line 310, in init
self.engine = self._init_engine(*args, **kwargs)
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/engine/async_llm_engine.py", line 415, in _init_engine
return engine_class(*args, **kwargs)
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/engine/llm_engine.py", line 106, in init
self.model_executor = executor_class(model_config, cache_config,
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/executor/gpu_executor.py", line 37, in init
self._init_worker()
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/executor/gpu_executor.py", line 66, in _init_worker
self.driver_worker.load_model()
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/worker/worker.py", line 106, in load_model
self.model_runner.load_model()
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/worker/model_runner.py", line 95, in load_model
self.model = get_model(
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/model_executor/model_loader.py", line 92, in get_model
model.load_weights(model_config.model, model_config.download_dir,
File "/data/haolu/workspace/vllm-gptq-gptq_hf/vllm/model_executor/models/qwen2.py", line 416, in load_weights
param = params_dict[name]
KeyError: 'model.layers.0.self_attn.k_proj.weight'