pci device '0000:01:00.4' has no available instances of 'nvidia-527' help?

K

K7890

New Member
Feb 26, 2025
4
0
1
Good afternoon, I decided to try to set up the Proxmox + VGPU package. I followed the instructions at https://pve.proxmox.com/wiki/NVIDIA_vGPU_on_Proxmox_VE#cite_note-driver-versions-8 to configure it.
When I run different graphics profiles, gives me errors: pci device '0000:01:01.5' has no available instances of 'nvidia-527'.
But at the same time, if you run virtual machines with the same profile, everything works.
Either I'm wrong, or something is not working for me.

i9-12900KF
RTX a6000
Proxmox 8.3.2
Current driver NVIDIA-GRID-Linux-KVM-550.144.02-550.144.03-553.62

3213.JPG
 
Last edited:
Hi,

can you post your vm config and maybe the output of 'nvidia-smi vgpu' ?

did you start multiple vms with vgpus?
 
nvidia-smi vgpu
1741070700343.png

ВМ соответствует графическим профилям, что приводит к успешному результату. Но в разных странах выдает ошибку.
1741070910779.png
pveversion -v

Code: 
proxmox-ve: 8.3.0 (рабочее ядро: 6.5.13-6-pve)
pve-manager: 8.3.4 (текущая версия: 8.3.4/65224a0f9cd294a3)
proxmox-kernel-helper: 8.1.0
проксмокс-ядро-6.8: 6.8.12-8
proxmox-kernel-6.8.12-8-pve-signed: 6.8.12-8
proxmox-kernel-6.8.12-4-pve-signed: 6.8.12-4
proxmox-kernel-6.5.13-6-pve-signed: 6.5.13-6
проксмокс-ядро-6.5: 6.5.13-6
цеф-предохранитель: 17.2.7-pve3
corosync: 3.1.7-pve3
criu: 3.17.1-2+deb12u1
glusterfs-клиент: 10.3-5
еслиupdown2: 3.2.0-1+pmx11
ksm-control-daemon: 1.5-1
libjs-extjs: 7.0.0-5
libknet1: 1.28-pve1
libproxmox-acme-perl: 1.5.1
libproxmox-backup-qemu0: 1.5.1
libproxmox-rs-perl: 0.3.4
libpve-access-control: 8.2.0
libpve-apiclient-perl: 3.3.2
libpve-кластер-api-perl: 8.0.10
libpve-кластер-perl: 8.0.10
libpve-common-perl: 8.2.9
libpve-гостевой-общий-perl: 5.1.6
libpve-http-сервер-perl: 5.2.0
libpve-сеть-perl: 0.10.0
libpve-rs-perl: 0.9.1
libpve-хранилище-perl: 8.3.3
libspice-server1: 0.15.1-1
лвм2: 2.03.16-2
lxc-pve: 6.0.0-1
lxcfs: 6.0.0-pve2
novnc-pve: 1.5.0-1
proxmox-резервное копирование-клиент: 3.3.3-1
proxmox-резервная копия-файл-восстановление: 3.3.3-1
proxmox-брандмауэр: 0.6.0
proxmox-kernel-helper: 8.1.0
proxmox-mail-forward: 0.3.1
proxmox-mini-journalreader: 1.4.0
proxmox-offline-mirror-helper: 0.6.7
proxmox-widget-toolkit: 4.3.4
pve-кластер: 8.0.10
pve-контейнер: 5.2.4
pve-документы: 8.3.1
pve-edk2-прошивка: 4.2023.08-4
pve-esxi-импорт-инструменты: 0.7.2
pve-брандмауэр: 5.1.0
pve-прошивка: 3.14-3
pve-ha-менеджер: 4.0.6
pve-i18n: 3.3.3
pve-qemu-kvm: 9.0.2-5
pve-xtermjs: 5.3.0-3
qemu-сервер: 8.3.8
smartmontools: 7.3-pve1
spiceterm: 3.3.0
swtpm: 0.8.0+pve1
vncterm: 1.8.0
zfsutils-linux: 2.2.7-pve1[/КОД]

Vm Configuration

Code: 
агент: 1
биос: ovmf
загрузка: order=scsi0;ide2;net0
ядер: 8
процессор: x86-64-v2-AES
efidisk0: local-lvm:vm-100-disk-0,efitype=4m,pre-enrolled-keys=1,size=4M
hostpci0: отображение=RTXA6000,mdev=nvidia-525,x-vga=1
машина: pc-q35-9.0,viommu=virtio
память: 8000
мета: создание-qemu=9.0.2,ctime=1740471833
имя: vdi01
net0: virtio=BC:24:11:44:66:18,мост=vmbr0,брандмауэр=1
число: 0
при загрузке: 1
тип_системы: win11
scsi0: local-lvm:vm-100-disk-1,cache=writeback,iothread=1,size=500G
scsihw: virtio-scsi-pci
smbios1: uuid=0112e566-d822-44c6-be7b-6cf490ba878d
розетки: 1
tpmstate0: local-lvm:vm-100-disk-2,размер=4M,версия=v2.0
vmgenid: 4f9fe718-ef72-4d5f-ac91-3495944e3d3d

Code: 
root@SRV-VDI01:~# nvidia-smi vgpu -c
GPU 00000000:01:00.0
    NVIDIA RTXA6000-24Q
    NVIDIA RTXA6000-24A
 
Last edited:
After a long search on the forum, I came across articles and documentation from NVIDIA
G

Thread 'vGPU with nVIDIA on Kernel 6.8'

Quite a few changes with vGPU software on Kernel 6.8. The feature is called "Vendor-Specific VFIO Framework".

Note you will need 550.90.05 for this to work which you can download from nVIDIA. Things like mixed size vGPU (you can now have different memory allocations on the same GPU) and live migration on KVM are now a feature (haven't tested that feature yet, more to come).
Note: current versions of the 535 and perhaps other branches may now work as well (which you may need if you are using Pascal-era (2014) hardware). Review "Vendor-Specific VFIO" under KVM portion of nVIDIA...
  • Like

But I don't have the nvidia catalog.

1741076877961.png
ls /sys/bus/pci/devices/0000:01:00.0

1741076980294.png
 
You must log in or register to reply here.
Top Bottom