Troubles with starting NVIDIA Persistence Daemon service (Ubuntu 16.04)

Hi! I just have installed CUDA Toolkit and was finishing post-installation actions. But I have troubles with starting NVIDIA Persistence Daemon service. I currently work on Ubuntu 16.04.6 LTS.

CUDA version:

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Wed_Oct_23_19:24:38_PDT_2019
Cuda compilation tools, release 10.2, V10.2.89

GPUs and driver version:

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 440.33.01    Driver Version: 440.33.01    CUDA Version: 10.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  Tesla V100-PCIE...  Off  | 00000000:8A:00.0 Off |                    0 |
| N/A   32C    P0    35W / 250W |      0MiB / 32510MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
|   1  Tesla V100-PCIE...  Off  | 00000000:8B:00.0 Off |                    0 |
| N/A   32C    P0    34W / 250W |      0MiB / 32510MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
|   2  Tesla V100-PCIE...  Off  | 00000000:9C:00.0 Off |                    0 |
| N/A   31C    P0    34W / 250W |      0MiB / 32510MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
|   3  Tesla V100-PCIE...  Off  | 00000000:9D:00.0 Off |                    0 |
| N/A   31C    P0    33W / 250W |      0MiB / 32510MiB |      2%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

What i get when try to start daemon service:

nvidia-persistenced.service - NVIDIA Persistence Daemon
   Loaded: loaded (/lib/systemd/system/nvidia-persistenced.service; enabled; vendor preset: enabled)
   Active: inactive (dead) since Sat 2020-01-25 04:41:08 MSK; 1s ago
  Process: 2152 ExecStopPost=/bin/rm -rf /var/run/nvidia-persistenced (code=exited, status=0/SUCCESS)
  Process: 2145 ExecStart=/usr/bin/nvidia-persistenced --no-persistence-mode --verbose (code=exited, status=0/SUCCESS)
 Main PID: 2147 (code=exited, status=0/SUCCESS)

Jan 25 04:41:08 nvidia-persistenced[2147]: device 0000:9c:00.0 - registered
Jan 25 04:41:08 nvidia-persistenced[2147]: device 0000:9d:00.0 - registered
Jan 25 04:41:08 nvidia-persistenced[2147]: device 0000:8a:00.0 - registered
Jan 25 04:41:08 nvidia-persistenced[2147]: device 0000:8b:00.0 - registered
Jan 25 04:41:08 nvidia-persistenced[2147]: Local RPC services initialized
Jan 25 04:41:08 systemd[1]: Started NVIDIA Persistence Daemon.
Jan 25 04:41:08 systemd[1]: Started NVIDIA Persistence Daemon.
Jan 25 04:41:08 nvidia-persistenced[2147]: Received signal 15
Jan 25 04:41:08 systemd[1]: Stopping NVIDIA Persistence Daemon...
Jan 25 04:41:08 systemd[1]: Stopped NVIDIA Persistence Daemon.

There was at least one post exactly about this kind of issue, but none of them helped me :(( Does anyone know how to solve this?