It was fine but stopped working after turning the server off.
When I replaced A6000 with GTX1060, GTX1060 was recognized by nvidia-smi.
I have no idea what to do anymore.
~$ hostnamectl
Operating System: Ubuntu 20.04.5 LTS
Kernel: Linux 5.4.160-0504160-generic
Architecture: x86-64
~$ lspci -vv | grep -i nvidia
41:00.0 VGA compatible controller: NVIDIA Corporation GA102GL [RTX A6000] (rev a1) (prog-if 00 [VGA controller])
Kernel driver in use: nvidia
Kernel modules: nvidiafb, nouveau, nvidia_drm, nvidia
41:00.1 Audio device: NVIDIA Corporation GA102 High Definition Audio Controller (rev a1)
~$ dkms status
nvidia, 525.53, 5.4.160-0504160-generic, x86_64: installed
nvidia, 525.78.01, 5.15.0-60-generic, x86_64: installed
nvidia, 525.78.01, 5.4.160-0504160-generic, x86_64: built
~$ sudo lshw -C display
*-display UNCLAIMED
description: VGA compatible controller
product: ASPEED Graphics Family
vendor: ASPEED Technology, Inc.
physical id: 0
bus info: pci@0000:2a:00.0
version: 41
width: 32 bits
clock: 33MHz
capabilities: pm msi vga_controller cap_list
configuration: latency=0
resources: memory:c0000000-c3ffffff memory:c4000000-c401ffff ioport:1000(size=128) memory:c0000-dffff
*-display
description: VGA compatible controller
product: GA102GL [RTX A6000]
vendor: NVIDIA Corporation
physical id: 0
bus info: pci@0000:41:00.0
version: a1
width: 64 bits
clock: 33MHz
capabilities: pm vga_controller bus_master cap_list rom
configuration: driver=nvidia latency=0
resources: iomemory:1040-103f iomemory:1040-103f irq:196 memory:f0000000-f0ffffff memory:10450000000-1045fffffff memory:104de000000-104dfffffff ioport:4000(size=128) memory:f1000000-f107ffff memory:f1080000-f203ffff memory:10060000000-1044fffffff memory:10460000000-104ddffffff
nvidia-bug-report.log (2.7 MB)