esxi 6.5u1 with Tesla M60 > driver not loading

Virtual GPU Forums More vGPU Forums NVIDIA Virtual GPU Technology
1

Hi there,

I am struggling with getting the nvidia driver loaded on a host with vmware 6.5u1.

Checking dmesg > Output:
[root@newhost:~] dmesg | grep -E "NVRM|nvidia"
2017-11-06T11:37:35.084Z cpu12:66798)Starting service nvidia-init
2017-11-06T11:37:35.085Z cpu12:66798)Activating Jumpstart plugin nvidia-init.
2017-11-06T11:37:35.287Z cpu12:66798)Jumpstart plugin nvidia-init activated.

[root@newhost:~] nvidia-smi
NVIDIA-SMI has failed because it couldn’t communicate with the NVIDIA driver. Make sure that the latest NVIDIA driver is installed and running.

I don’t have a clue why it doesn’t load it. I tried both:
NVIDIA-vGPU-kepler-vSphere-6.5-367.106-370.12
NVIDIA-vGPU-kepler-vSphere-6.5-367.122-370.16
…without success.

Anyone a hint what else to try or to do?

Paul

2

You’re using the wrong vGPU manager. Kepler won’t work for Maxwell!!!

3

I’m having issues. This is the driver that by all accounts I should have installed (and I have):

NVIDIA-VMware_ESXi_6.5_Host_Driver 384.73-1OEM.650.0.0.4598673 NVIDIA VMwareAccepted 2017-11-09

When I attach a vGPU profile to my Windows 7 vm and attempt to power-on I get the following error "The amount of graphics resource available in the parent resource pool is insufficient for the operation." It seems to point to this VMware KB:
https://kb.vmware.com/s/article/2126577

Once again I believe I’ve installed the correct VIB, but the kb says it should say vGPU in the description. If I’ve installed the incorrect vib, where do I get the correct one?

4

Resolution was related to this article:

https://gridforums.nvidia.com/default/topic/1030/nvidia-vmware-vsphere-6-5/