k3s 节点重启后，GPU虚拟化失效，nvidia.com/gpu 数目变回物理GPU数目，重启pod hami-device-plugin后，nvidia.com/gpu 数目恢复正常

[christu]

What happened:
k3s 节点重启后，GPU虚拟化失效，nvidia.com/gpu 数目变回物理GPU数目，重启pod hami-device-plugin后，nvidia.com/gpu 数目恢复正常

What you expected to happen:

How to reproduce it (as minimally and precisely as possible):

Anything else we need to know?:

• The output of nvidia-smi -a on your host
• Your docker or containerd configuration file (e.g: /etc/docker/daemon.json)
• The hami-device-plugin container logs
• The hami-scheduler container logs
• The kubelet logs on the node (e.g: sudo journalctl -r -u kubelet)
• Any relevant kernel output lines from dmesg

Environment:

• HAMi version: v2.3.13
• nvidia driver or other AI device driver version:
• Docker version from docker version
• Docker command, image and tag used
• Kernel version from uname -a
• Others:

[archlitchi]

你应该是之前没卸载掉nvidiade device-plugin吧

[christu]

你应该是之前没卸载掉nvidiade device-plugin吧

先安装的nvidia GPU Opeartor，再安装的Hami，安装完hami之后需要把 nvidia-device-plugin-daemonset 卸载掉吗？

[archlitchi]

你应该是之前没卸载掉nvidiade device-plugin吧

先安装的nvidia GPU Opeartor，再安装的Hami，安装完hami之后需要把 nvidia-device-plugin-daemonset 卸载掉吗？

是的，除非你用自定义的资源名

[christu]

好的，了解了，多谢！

[christu]

在安装 nvidia GPU Opeartor 之后，删除 nvidia-device-plugin-daemonset 的方法吗？尝试删除nvidia-device-plugin-daemonset ，但删除后就会重新创建

[christu]

你应该是之前没卸载掉nvidiade device-plugin吧

先安装的nvidia GPU Opeartor，再安装的Hami，安装完hami之后需要把 nvidia-device-plugin-daemonset 卸载掉吗？

是的，除非你用自定义的资源名

在安装 nvidia GPU Opeartor 之后，有删除 nvidia-device-plugin-daemonset 的方法吗？尝试删除nvidia-device-plugin-daemonset ，但删除后就会重新创建

[w7team]

关注一下这个问题。目前文档里没说要删掉nvidia-device-plugin-daemonset