mdev instance failed; multiple VM's

[KingAllen]

I'm using it for vGPU multiple VM's. I have now 1VM and using it for gaming and when I create another VM and share the vGPU I got error.

I choose this in mdevctl;

nvidia-259
    Available instances: 6
    Device API: vfio-pci
    Name: GRID RTX6000-4Q
    Description: num_heads=4, frl_config=60, framebuffer=4096M, max_resolution=7680x4320, max_instance=6

and when I create another VM my nvidia-259 goes to this.

 nvidia-259
    Available instances: 4
    Device API: vfio-pci
    Name: GRID RTX6000-4Q
    Description: num_heads=4, frl_config=60, framebuffer=4096M, max_resolution=7680x4320, max_instance=6

After adding vGPU in VM2 in PCI Device and start the VM I got this error.

root@CLG:~# qm start 302
mdev instance '00000000-0000-0000-0000-000000000302' already existed, using it.
kvm: -device vfio-pci,sysfsdev=/sys/bus/pci/devices/0000:44:00.0/00000000-0000-0000-0000-000000000302,id=hostpci0,bus=pci.0,addr=0x10: warning: vfio 00000000-0000-0000-0000-000000000302: Could not enable error recovery for the device
kvm: -device vfio-pci,sysfsdev=/sys/bus/pci/devices/0000:44:00.0/00000000-0000-0000-0000-000000000302,id=hostpci0,bus=pci.0,addr=0x10: vfio 00000000-0000-0000-0000-000000000302: failed to read device config space: Bad address
start failed: QEMU exited with code 1

Can anyone help me to this.