Hi everyone,
We are an NVIDIA Inception member and are currently evaluating a virtualized GPU setup for internal development and supporting workloads.
Our intended setup includes:
-
A single physical GPU
-
Two isolated virtual machines
-
Shared GPU access using NVIDIA vGPU technology
Our understanding is that NVIDIA RTX Virtual Workstation (RTX vWS) would be the appropriate solution for this architecture, requiring two (2) CCUs/licenses for concurrent vGPU access.
We would appreciate guidance on:
-
Whether RTX vWS is the correct licensing model for this use case
-
General best practices for vGPU allocation across multiple VMs
-
Recommended next steps or Inception-specific paths for accessing RTX vWS
Thank you in advance for any direction you can provide.