atlas200加速模块RC模式,物理机能够正常运行mindspore_serving 2.0.0,在容器内运行报错
收藏回复举报
atlas200加速模块RC模式,物理机能够正常运行mindspore_serving 2.0.0,在容器内运行报错
t('forum.solved') 已解决
发表于2023-09-20 21:16:44
0 查看

首先,atlas200加速模块RC模式, 物理机安装了python3.7.5+mindspore2.0+mindspore_serving2.0和cann-toolkits,能够实现正常运行mindspore_serving推理服务。

随后,构造docker推理容器,挂载物理机python环境目录,挂载物理机cann-toolkits工作目录,npm-smi info、atc --help、pyacl加载om模型等功能都能够正常运行,但是mindspore_serving推理服务报错,关键信息如下:

root@a1ef4bd5548d: python serving_server.py
---
Serving: Master server start success, listening on unix:unix_socket_files/serving_master_284
---
Traceback (most recent call last):
  File "mytest/serving_server.py", line 16, in <module>
    start()
  File "mytest/serving_server.py", line 10, in start
    server.start_servables(servable_configs=servable_config)
  File "/root/miniconda3/envs/py375/lib/python3.7/site-packages/mindspore_serving/server/master/_master.py", line 63, in handle_except
    func(*args, **kwargs)
  File "/root/miniconda3/envs/py375/lib/python3.7/site-packages/mindspore_serving/server/_server.py", line 119, in start_servables
    _listening_workers_when_startup(worker_list)
  File "/root/miniconda3/envs/py375/lib/python3.7/site-packages/mindspore_serving/server/_server.py", line 231, in _listening_workers_when_startup
    raise RuntimeError(f"Fail to start workers: {worker.get_notified_error()}")
---
RuntimeError: Fail to start workers: {servable name:mytest, device id:0, <Raise failed: Load model failed, servable directory: '/home/HwHiAiUser/xc200/mytest', servable name: 'mytest', model file: '[mytest-018.mindir]', version number 1,model context: {}, load error details: Common error code.>}

bash 输出

日志内容

[ERROR] ME(1345,fffeffff5a90,python):2023-09-20-13:58:36.600.421 [mindspore/ccsrc/cxx_api/model/acl/model_converter.cc:152] BuildAirModel] Call aclgrphBuildInitialize fail.
[ERROR] ME(1345,fffeffff5a90,python):2023-09-20-13:58:36.732.976 [mindspore/ccsrc/cxx_api/model/acl/model_converter.cc:389] operator()] Convert model from MindIR to OM failed
[ERROR] ME(1345,fffeffff5a90,python):2023-09-20-13:58:36.757.505 [mindspore/ccsrc/cxx_api/model/model_converter_utils/multi_process.cc:140] ChildProcess] Child process process failed
[WARNING] ME(1304,fffec375b1f0,python):2023-09-20-13:58:36.805.617 [mindspore/ccsrc/cxx_api/model/model_converter_utils/multi_process.cc:228] HeartbeatThreadFuncInner] Peer stopped
[ERROR] ME(1304,fffeffff5a90,python):2023-09-20-13:58:36.808.890 [mindspore/ccsrc/cxx_api/model/acl/model_converter.cc:369] operator()] Receive result model from child process failed
[ERROR] ME(1304,fffeffff5a90,python):2023-09-20-13:58:36.833.215 [mindspore/ccsrc/cxx_api/model/model_converter_utils/multi_process.cc:118] ParentProcess] Parent process process failed
[ERROR] ME(1304,fffeffff5a90,python):2023-09-20-13:58:37.885.322 [mindspore/ccsrc/cxx_api/model/acl/model_converter.cc:403] LoadMindIR] Convert MindIR model to OM model failed
[ERROR] ME(1304,fffeffff5a90,python):2023-09-20-13:58:37.885.418 [mindspore/ccsrc/cxx_api/model/acl/acl_model.cc:79] Build] Load MindIR failed.
Your Code

本帖最后由 匿名用户2023/09/20 22:00:48 编辑

我要发帖子