Azure自动化ML模型部署至实时终端失败求助

我在Azure Machine Learning Studio中使用Azure Automated ML构建并成功注册模型，但部署至实时终端时持续报错，错误详情如下：

Instance status:
SystemSetup: Succeeded
UserContainerImagePull: Succeeded
ModelDownload: Succeeded
UserContainerStart: InProgress
 

Container events:
Kind: Pod, Name: Downloading, Type: Normal, Time: 2025-01-16T14:42:49.04805Z, Message: Start downloading models
Kind: Pod, Name: Pulling, Type: Normal, Time: 2025-01-16T14:42:49.2168Z, Message: Start pulling container image
Kind: Pod, Name: Pulled, Type: Normal, Time: 2025-01-16T14:50:50.914779Z, Message: Container image is pulled successfully
Kind: Pod, Name: Downloaded, Type: Normal, Time: 2025-01-16T14:50:50.914779Z, Message: Models are downloaded successfully
Kind: Pod, Name: Created, Type: Normal, Time: 2025-01-16T14:50:50.942294Z, Message: Created container inference-server
Kind: Pod, Name: Failed, Type: Warning, Time: 2025-01-16T14:50:51.116795Z, Message: Error: failed to create containerd task: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: exec: "runsvdir": executable file not found in $PATH: unknown

从日志可见，模型文件、容器镜像均已成功下载拉取，但容器启动时提示runsvdir可执行文件不在$PATH中，推测Azure部署镜像缺少必要组件。以下是将问题升级反馈给微软的几种方式：

• Azure门户提交支持请求
  • 登录Azure门户，定位到对应的Azure Machine Learning工作区
  • 左侧导航栏选择「支持 + 故障排除」->「新建支持请求」
  • 问题分类选择「机器学习」->「Azure Machine Learning服务」->「部署」
  • 提交时附上完整报错日志、工作区ID、部署名称、模型名称及版本、AutoML实验ID等关键信息
• Azure ML Studio内直接反馈
  • 打开Azure ML Studio，进入报错的部署页面
  • 点击右上角问号图标，选择「反馈问题」或「联系支持」
  • 填写问题描述并上传报错日志及相关资源信息
• Azure CLI提交支持请求
  • 执行az support tickets create命令，指定服务名称、问题类型、详细描述及相关资源ID，具体参数可通过az support tickets create --help查询

内容的提问来源于stack exchange，提问作者phil