Cuda, Nvidia GPU and VMware ESXI 6.5

Hi I don’t know if people in here maybe able to help but ill ask anyway

I am trying to get a Tesla M60 Card in PCI Passthrough mode to a Windows Box hosted in ESXi 6.5, to be used as a compute resource not graphics.

I’m struggling a bit with getting the card into compute mode and being able to boot the VM, if I leave it in Graphics mode I can boot no issue, and am then able to put into compute mode in windows but cannot get the CUDA Toolkit to recognise it.

I’m really hoping someone can help or point me in the right direction of a forum or guide that may help…ive followed the guides supplied by NVDIA and it doesn’t work as expected