multiple gpus in azure linux vm

I have four gpus in an azure rhel 7.2 vm. I have been able to create multi-seat and start 4 xservers, but it looks like all four are running on the same gpu not each running on a different one. Is nvidia-smi wrong?

zneusu3n21st0ec-71> nvidia-smi
Fri Aug 17 20:07:35 2018
±----------------------------------------------------------------------------+
| NVIDIA-SMI 384.111 Driver Version: 384.111 |
|-------------------------------±---------------------±---------------------+
| 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 M60 On | 0000066D:00:00.0 Off | Off |
| N/A 33C P8 12W / 150W | 208MiB / 8123MiB | 1% Default |
±------------------------------±---------------------±---------------------+
| 1 Tesla M60 On | 00002007:00:00.0 Off | Off |
| N/A 30C P8 14W / 150W | 1MiB / 8123MiB | 0% Default |
±------------------------------±---------------------±---------------------+
| 2 Tesla M60 On | 00003CA5:00:00.0 Off | Off |
| N/A 35C P8 13W / 150W | 0MiB / 8123MiB | 0% Default |
±------------------------------±---------------------±---------------------+
| 3 Tesla M60 On | 00006361:00:00.0 Off | Off |
| N/A 26C P8 12W / 150W | 0MiB / 8123MiB | 0% Default |
±------------------------------±---------------------±---------------------+

±----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 20250 G /usr/bin/X 36MiB |
| 0 20251 G /usr/bin/X 36MiB |
| 0 20252 G /usr/bin/X 50MiB |
| 0 20253 G /usr/bin/X 36MiB |
| 0 20420 G /usr/bin/gnome-shell 9MiB |
| 0 20429 G /usr/bin/gnome-shell 11MiB |
| 0 20433 G /usr/bin/gnome-shell 8MiB |
| 0 20585 G /usr/bin/gnome-shell 9MiB |
| 0 96951 G …ver/3rdparty/virtualgl/bin/glxspheres64 6MiB |
±----------------------------------------------------------------------------+