Atlas 800I Qwen2.5-1.5B的MindIE服务化失败:
收藏回复举报
Atlas 800I Qwen2.5-1.5B的MindIE服务化失败:
t('forum.solved') 已解决
新人帖
发表于2025-05-30 10:34:03
0 查看

MindIE版本:1.0.0

CANN:8.0.0

驱动:24.1.rc3

启服务化命令:./bin/mindieservice_daemon

报错信息:

(PyTorch-2.1.0) [root mindie-service]$./bin/mindieservice_daemon  

2025-05-30 10:04:08,332 [INFO] config.py:30 - model_config {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '0', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/usr/local/Ascend/data/Qwen2.5-1.5B', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'Qwen2.5-1.5B', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '0', 'npu_device_ids': '0', 'npu_mem': '-1', 'pp': '0', 'rank': '0', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '0', 'world_size': '1'} 

2025-05-30 10:04:08,332 [INFO] config.py:35 - do not init dmi config 

2025-05-30 10:04:08,332 [INFO] standard_model.py:145 - rank id 0 get model config: {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '0', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/usr/local/Ascend/data/Qwen2.5-1.5B', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'Qwen2.5-1.5B', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '0', 'npu_device_ids': '0', 'npu_mem': '-1', 'pp': '0', 'rank': '0', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '0', 'world_size': '1'} 

2025-05-30 10:04:10,305 [ERROR] model.py:39 - [Model]   >>> Exception:expected str, bytes or os.PathLike object, not NoneType 

Traceback (most recent call last): 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/model_wrapper/model.py", line 37, in initialize 

    return self.python_model.initialize(config) 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 146, in initialize 

    self.generator = Generator( 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 79, in __init__ 

    self.generator_backend = get_generator_backend(model_config) 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/__init__.py", line 26, in get_generator_backend 

    return generator_cls(model_config) 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 96, in __init__ 

    super().__init__(model_config) 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 107, in __init__ 

    self.model_wrapper = get_model_wrapper(model_config, backend_type) 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/__init__.py", line 7, in get_model_wrapper 

    from .atb.atb_model_wrapper import ATBModelWrapper 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 8, in <module> 

    from atb_llm.runner.model_runner import ModelRunner 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/atb_llm/runner/model_runner.py", line 12, in <module> 

    import atb_llm.nn as atb_llm_nn 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/atb_llm/nn/__init__.py", line 3, in <module> 

    from atb_llm.nn.modules import ( 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/atb_llm/nn/modules/__init__.py", line 6, in <module> 

    from .normalization import RmsNorm as RmsNorm 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/atb_llm/nn/modules/normalization.py", line 5, in <module> 

    from ..network import Tensor, Node, get_default_net 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/atb_llm/nn/network.py", line 10, in <module> 

    sys.path.append(os.path.join(path, 'lib')) 

  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/posixpath.py", line 76, in join 

    a = os.fspath(a) 

TypeError: expected str, bytes or os.PathLike object, not NoneType 

2025-05-30 10:04:10,307 [ERROR] model.py:42 - [Model]   >>> return initialize error result: {'status': 'error', 'npuBlockNum': '0', 'cpuBlockNum': '0'} 

Daemon is killing... 

Killed

报错日志:

[2025-05-30 10:04:02.537+08:00] [1235847] [1235849] [server] [INFO] [connector_launcher.cpp:124] : Child handler has been registered, register is back. 

[2025-05-30 10:04:02.537+08:00] [1235847] [1235849] [server] [INFO] [share_memory.cpp:167] : total shared memory size:1.50576e+06MB, and available shared memory size:1.50576e+06MB. 

[2025-05-30 10:04:02.537+08:00] [1235847] [1235849] [server] [INFO] [share_memory.cpp:168] : [ShareMemory::SharedMemorySizeCheck] shared memory size check success. 

[2025-05-30 10:04:02.553+08:00] [1235847] [1235849] [server] [INFO] [share_memory.cpp:167] : total shared memory size:1.50576e+06MB, and available shared memory size:1.50573e+06MB. 

[2025-05-30 10:04:02.553+08:00] [1235847] [1235849] [server] [INFO] [share_memory.cpp:168] : [ShareMemory::SharedMemorySizeCheck] shared memory size check success. 

[2025-05-30 10:04:02.568+08:00] [1235847] [1235849] [server] [INFO] [share_memory.cpp:167] : total shared memory size:1.50576e+06MB, and available shared memory size:1.5057e+06MB. 

[2025-05-30 10:04:02.568+08:00] [1235847] [1235849] [server] [INFO] [share_memory.cpp:168] : [ShareMemory::SharedMemorySizeCheck] shared memory size check success. 

[2025-05-30 10:04:10.366036+08:00] [1235847] [1235849] [server] [WARN] [llm_daemon.cpp:64] : [Daemon] received exit signal[17] 

[2025-05-30 10:04:10.366116+08:00] [1235847] [1235849] [server] [INFO] [llm_daemon.cpp:69] : Daemon wait pid with 1236204, status 9 

[2025-05-30 10:04:10.366123+08:00] [1235847] [1235849] [server] [ERROR] [llm_daemon.cpp:74] : ERR: Daemon wait pid with 1236204 exit, Please check the service log or python log.

我要发帖子