VGPU A6000 set up and installation

[Nforvgpu]

I am trying to set up a VGPU for the RTX A6000 and I can seem to get the vgpu set up.

I have installed the drivers:
NVIDIA-Linux-x86_64-550.127.05-grid.run


when i type the nvidia-smi it finds the driver:

Wed Dec 18 20:27:10 2024 +-----------------------------------------------------------------------------------------+| NVIDIA-SMI 550.127.05 Driver Version: 550.127.05 CUDA Version: 12.4 ||-----------------------------------------+------------------------+----------------------+| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC || Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. || | | MIG M. ||=========================================+========================+======================|| 0 NVIDIA RTX A6000 On | 00000000:E1:00.0 Off | Off || 30% 35C P8 22W / 300W | 2MiB / 49140MiB | 0% Default || | | N/A |+-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+| Processes: || GPU GI CI PID Type Process name GPU Memory || ID ID Usage ||=========================================================================================|| No running processes found |+-----------------------------------------------------------------------------------------+

However I cant seem to find the VGPU to assign to the VMs.

When I run
dkms status
nvidia/550.127.05, 6.8.12-5-pve, x86_64: installed


ls /sys/class/mdev_bus/
ls: cannot access '/sys/class/mdev_bus/': No such file or directory

What am I doing wrong? Is there anything I should be doing from here. I am completely new to this.

Many thanks,

N

 

[cheiss]

Hi,

have you followed our wiki guide for vGPU? https://pve.proxmox.com/wiki/NVIDIA_vGPU_on_Proxmox_VE
Have you enabled SR-IOV?

 

[Nforvgpu]

Hi,

have you followed our wiki guide for vGPU? https://pve.proxmox.com/wiki/NVIDIA_vGPU_on_Proxmox_VE
Have you enabled SR-IOV?

This appears to be the issue. I have followed all the steps. Its has installed correctly. But the SR-IOV want initiate. Its permissioned on the BIOS and Ioumm is working.

The install is correct however I get:
sudo /usr/lib/nvidia/sriov-manage -e ALL
sudo: /usr/lib/nvidia/sriov-manage: command not found


ls /sys/class/mdev_bus/
ls: cannot access '/sys/class/mdev_bus/': No such file or directory

cat /sys/bus/pci/devices/0000:e1:00.0/sriov_numvfscat: '/sys/bus/pci/devices/0000:e1:00.0/sriov_numvfs': No such file or directory