Questions about vGPU with OpenNebula

Product Support Operations
1

Hello,

I’m going to add a new node that will share a Nvidia GPU card. I have some questions (I have yet read “vGPU” chapter) I would like to have answered before to start node installation:

  1. In my scenario, node that will serve and share a GPU will be a KVM hypervisor that is not the frontend. I suppose that in this new KVM hypervisor, I will need to install Nvidia drivers to allow a correct detection of the Nvidia card.
  2. vGPU Nvidia licenses (mandatory to allow share and divide GPU) need to be installed in the KVM hypervisor that has physically installed GPU card, isn’t it?

With these two questions answered, I think I could start with this new project… Sure there will be more questions about vGPU integration with OpenNebula, but let’s take it one step at a time.

Thanks.

2

Hello,

The answer to both questions is yes. Please, check the documentation page in

Cheers!

1 Like
3

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.