INFO 03-21 14:36:16 model_runner.py:1113] Starting to load model /data/models/modelscope/Qwen/QwQ-32B-AWQ...

Loading safetensors checkpoint shards: 0% Completed | 0/5 [00:00<?, ?it/s]

Loading safetensors checkpoint shards: 20% Completed | 1/5 [00:01<00:06, 1.73s/it]

Loading safetensors checkpoint shards: 40% Completed | 2/5 [00:03<00:05, 1.78s/it]

Loading safetensors checkpoint shards: 60% Completed | 3/5 [00:05<00:03, 1.88s/it]

ERROR 03-21 14:36:44 engine.py:389] start out of range (expected to be in range of [-640, 640], but got 3456)

ERROR 03-21 14:36:44 engine.py:389] Traceback (most recent call last):

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 380, in run_mp_engine

ERROR 03-21 14:36:44 engine.py:389] engine = MQLLMEngine.from_engine_args(engine_args=engine_args,

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 123, in from_engine_args

ERROR 03-21 14:36:44 engine.py:389] return cls(ipc_path=ipc_path,

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 75, in init

ERROR 03-21 14:36:44 engine.py:389] self.engine = LLMEngine(*args, **kwargs)

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 274, in init

ERROR 03-21 14:36:44 engine.py:389] self.model_executor = executor_class(vllm_config=vllm_config, )

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/executor/executor_base.py", line 51, in init

ERROR 03-21 14:36:44 engine.py:389] self._init_executor()

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/executor/uniproc_executor.py", line 42, in _init_executor

ERROR 03-21 14:36:44 engine.py:389] self.collective_rpc("load_model")

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/executor/uniproc_executor.py", line 51, in collective_rpc

ERROR 03-21 14:36:44 engine.py:389] answer = run_method(self.driver_worker, method, args, kwargs)

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/utils.py", line 2313, in run_method

ERROR 03-21 14:36:44 engine.py:389] return func(*args, **kwargs)

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/worker/worker.py", line 183, in load_model

ERROR 03-21 14:36:44 engine.py:389] self.model_runner.load_model()

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/worker/model_runner.py", line 1115, in load_model

ERROR 03-21 14:36:44 engine.py:389] self.model = get_model(vllm_config=self.vllm_config)

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/model_loader/init.py", line 14, in get_model

ERROR 03-21 14:36:44 engine.py:389] return loader.load_model(vllm_config=vllm_config)

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/model_loader/loader.py", line 388, in load_model

ERROR 03-21 14:36:44 engine.py:389] loaded_weights = model.load_weights(

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/qwen2.py", line 683, in load_weights

ERROR 03-21 14:36:44 engine.py:389] return loader.load_weights(weights)

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 235, in load_weights

ERROR 03-21 14:36:44 engine.py:389] autoloaded_weights = set(self._load_module("", self.module, weights))

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 196, in _load_module

ERROR 03-21 14:36:44 engine.py:389] yield from self._load_module(prefix,

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 173, in _load_module

ERROR 03-21 14:36:44 engine.py:389] loaded_params = module_load_weights(weights)

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/qwen2.py", line 425, in load_weights

ERROR 03-21 14:36:44 engine.py:389] weight_loader(param, loaded_weight, shard_id)

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/layers/linear.py", line 682, in weight_loader_v2

ERROR 03-21 14:36:44 engine.py:389] param.load_merged_column_weight(loaded_weight=loaded_weight,

ERROR 03-21 14:36:44 engine.py:389] File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/parameter.py", line 125, in load_merged_column_weight

ERROR 03-21 14:36:44 engine.py:389] param_data = param_data.narrow(self.output_dim, shard_offset,

ERROR 03-21 14:36:44 engine.py:389] IndexError: start out of range (expected to be in range of [-640, 640], but got 3456)

Process SpawnProcess-1:

Traceback (most recent call last):

File "/usr/local/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap

self.run()

File "/usr/local/lib/python3.10/multiprocessing/process.py", line 108, in run

self._target(*self._args, **self._kwargs)

File "/usr/local/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 391, in run_mp_engine

raise e

File "/usr/local/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 380, in run_mp_engine

engine = MQLLMEngine.from_engine_args(engine_args=engine_args,

File "/usr/local/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 123, in from_engine_args

return cls(ipc_path=ipc_path,

File "/usr/local/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 75, in init

self.engine = LLMEngine(*args, **kwargs)

File "/usr/local/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 274, in init

self.model_executor = executor_class(vllm_config=vllm_config, )

File "/usr/local/lib/python3.10/site-packages/vllm/executor/executor_base.py", line 51, in init

self._init_executor()

File "/usr/local/lib/python3.10/site-packages/vllm/executor/uniproc_executor.py", line 42, in _init_executor

self.collective_rpc("load_model")

File "/usr/local/lib/python3.10/site-packages/vllm/executor/uniproc_executor.py", line 51, in collective_rpc

answer = run_method(self.driver_worker, method, args, kwargs)

File "/usr/local/lib/python3.10/site-packages/vllm/utils.py", line 2313, in run_method

return func(*args, **kwargs)

File "/usr/local/lib/python3.10/site-packages/vllm/worker/worker.py", line 183, in load_model

self.model_runner.load_model()

File "/usr/local/lib/python3.10/site-packages/vllm/worker/model_runner.py", line 1115, in load_model

self.model = get_model(vllm_config=self.vllm_config)

File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/model_loader/init.py", line 14, in get_model

return loader.load_model(vllm_config=vllm_config)

File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/model_loader/loader.py", line 388, in load_model

loaded_weights = model.load_weights(

File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/qwen2.py", line 683, in load_weights

return loader.load_weights(weights)

File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 235, in load_weights

autoloaded_weights = set(self._load_module("", self.module, weights))

File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 196, in _load_module

yield from self._load_module(prefix,

File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 173, in _load_module

loaded_params = module_load_weights(weights)

File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/qwen2.py", line 425, in load_weights

weight_loader(param, loaded_weight, shard_id)

File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/layers/linear.py", line 682, in weight_loader_v2

param.load_merged_column_weight(loaded_weight=loaded_weight,

File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/parameter.py", line 125, in load_merged_column_weight

param_data = param_data.narrow(self.output_dim, shard_offset,

IndexError: start out of range (expected to be in range of [-640, 640], but got 3456)

Loading safetensors checkpoint shards: 60% Completed | 3/5 [00:26<00:17, 8.98s/it]

Traceback (most recent call last):

File "/root/.local/share/pipx/venvs/gpustack/bin/vllm", line 8, in <module>

sys.exit(main())

File "/usr/local/lib/python3.10/site-packages/vllm/scripts.py", line 204, in main

args.dispatch_function(args)

File "/usr/local/lib/python3.10/site-packages/vllm/scripts.py", line 44, in serve

uvloop.run(run_server(args))

File "/usr/local/lib/python3.10/site-packages/uvloop/init.py", line 82, in run

return loop.run_until_complete(wrapper())

File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete

File "/usr/local/lib/python3.10/site-packages/uvloop/init.py", line 61, in wrapper

return await main

File "/usr/local/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 875, in run_server

async with build_async_engine_client(args) as engine_client:

File "/usr/local/lib/python3.10/contextlib.py", line 199, in aenter

return await anext(self.gen)

File "/usr/local/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 136, in build_async_engine_client

async with build_async_engine_client_from_engine_args(

File "/usr/local/lib/python3.10/contextlib.py", line 199, in aenter

return await anext(self.gen)

File "/usr/local/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 230, in build_async_engine_client_from_engine_args

raise RuntimeError(

RuntimeError: Engine process failed to start. See stack trace for the root cause.