NVIDIA® RTX Virtual Workstation (vWS), NVIDIA Virtual PC (vPC), NVIDIA Virtual Applications (vApps), and NVIDIA Virtual Compute Server are available as licensed products on supported NVIDIA data centre GPUs.
NVIDIA vGPU deployments require a licence. When booted on a supported GPU, a vGPU runs with full capability. As long as the system remains unlicensed, the vGPU performance/functionality is progressively degraded over time where restrictions will be applied.
The performance/functionality of an unlicensed vGPU is restricted as follows:
Frame rate is capped at 3 frames per second.
GPU resource allocations are limited, which will prevent some applications from running correctly.
On vGPUs that support CUDA, CUDA is disabled.
These restrictions are removed when a licence is acquired.
To operate at full capability, a physical GPU running in GPU pass-through mode or a bare-metal deployment requires a vWS licence. You can also operate a physical GPU in pass-through mode or a bare-metal deployment at reduced capability with a vApps licence. vPC is not available on GPUs running in pass-through mode or bare-metal deployments.
A physical GPU with a vWS licence supports multiple virtual display heads at resolutions up to 8K and flexible virtual display resolutions based on the number of available pixels. For details, see Display Resolutions for Physical GPUs in Virtual GPU Client Licensing User Guide.
©2022 NVIDIA Corporation. All rights reserved. Licensing