All GPU memory in use and no program running

Hi,

I use an ec2 server g2.2xlarge with GRID K520.
I’m wondering why the GPU reports that all memory is in use, reported with nvidia-smi.
I’m the only user on the server and don’t run any application.

FB Memory Usage
Total : 4095 MiB
Used : 4052 MiB
Free : 43 MiB

When I use GPU-Z to monitor the metrics, I see
Memory Usage (Dedicated):118 MB
Memory Usage (Dynamic): 19MB

C:\Program Files\NVIDIA Corporation\NVSMI>nvidia-smi -i 0 -q

==============NVSMI LOG==============

Timestamp : Tue May 09 23:21:12 2017
Driver Version : 337.88

Attached GPUs : 1
GPU 0000:00:03.0
Product Name : GRID K520
Display Mode : Disabled
Display Active : Disabled
Persistence Mode : N/A
Accounting Mode : Disabled
Accounting Mode Buffer Size : 128
Driver Model
Current : WDDM
Pending : WDDM
Serial Number : 0325213073507
GPU UUID : GPU-4cc386c7-1511-e998-f8f8-c3fe800a90
Minor Number : N/A
VBIOS Version : 80.04.D4.00.03
Inforom Version
Image Version : 2055.0052.00.04
OEM Object : 1.1
ECC Object : N/A
Power Management Object : N/A
GPU Operation Mode
Current : N/A
Pending : N/A
PCI
Bus : 0x00
Device : 0x03
Domain : 0x0000
Device Id : 0x118A10DE
Bus Id : 0000:00:03.0
Sub System Id : 0x101410DE
GPU Link Info
PCIe Generation
Max : 3
Current : 1
Link Width
Max : 16x
Current : 16x
Bridge Chip
Type : N/A
Firmware : N/A
Fan Speed : N/A
Performance State : P8
Clocks Throttle Reasons : N/A
FB Memory Usage
Total : 4095 MiB
Used : 4052 MiB
Free : 43 MiB
BAR1 Memory Usage
Total : 128 MiB
Used : 37 MiB
Free : 91 MiB
Compute Mode : Default
Utilization
Gpu : 0 %
Memory : 0 %
Ecc Mode
Current : N/A
Pending : N/A
ECC Errors
Volatile
Single Bit
Device Memory : N/A
Register File : N/A
L1 Cache : N/A
L2 Cache : N/A
Texture Memory : N/A
Total : N/A
Double Bit
Device Memory : N/A
Register File : N/A
L1 Cache : N/A
L2 Cache : N/A
Texture Memory : N/A
Total : N/A
Aggregate
Single Bit
Device Memory : N/A
Register File : N/A
L1 Cache : N/A
L2 Cache : N/A
Texture Memory : N/A
Total : N/A
Double Bit
Device Memory : N/A
Register File : N/A
L1 Cache : N/A
L2 Cache : N/A
Texture Memory : N/A
Total : N/A
Retired Pages
Single Bit ECC : N/A
Double Bit ECC : N/A
Pending : N/A
Temperature
Gpu : 24 C
Power Readings
Power Management : Supported
Power Draw : 17.45 W
Power Limit : 125.00 W
Default Power Limit : 125.00 W
Enforced Power Limit : 125.00 W
Min Power Limit : 85.00 W
Max Power Limit : 130.00 W
Clocks
Graphics : 324 MHz
SM : 324 MHz
Memory : 324 MHz
Applications Clocks
Graphics : N/A
Memory : N/A
Default Applications Clocks
Graphics : N/A
Memory : N/A
Max Clocks
Graphics : 797 MHz
SM : 797 MHz
Memory : 2500 MHz
Compute Processes
Process ID : 1664
Name : Insufficient Permissions
Used GPU Memory : Not available in WDDM driver model
Process ID : 1588
Name : Insufficient Permissions
Used GPU Memory : Not available in WDDM driver model
Process ID : 1760
Name : Insufficient Permissions
Used GPU Memory : Not available in WDDM driver model
Process ID : 5396
Name : Insufficient Permissions
Used GPU Memory : Not available in WDDM driver model
Process ID : 6208
Name : C:\Windows\Explorer.EXE
Used GPU Memory : Not available in WDDM driver model

Here’s why:
https://developer.download.nvidia.com/compute/DCGM/docs/nvidia-smi-367.38.pdf

GPU Memory Usage
Amount of memory used on the device by the context. Not available on Windows when running in WDDM mode because Windows KMD manages all the memory not NVIDIA driver.