This application note details the packaging, pricing models, and licensing options for NVIDIA Virtual GPU (vGPU) software products.
This guide provides a high-level overview of the entitlement, packaging, and licensing for the NVIDIA virtual GPU (vGPU) software family. It serves as a quick reference to understand the product portfolio and corresponding SKU information without replacing the End User License Agreement (EULA).
The document outlines various vGPU solutions including NVIDIA Virtual Applications (vApps), NVIDIA Virtual PC (vPC), NVIDIA RTX Virtual Workstation (vWS), and NVIDIA Virtual Compute Server (vCS). It also lists supported graphics cards across Maxwell, Pascal, Turing, Volta, Ampere, and Ada architectures.
| Supported Maxwell GPUs | M10, M60, M6 |
|---|---|
| Supported Pascal GPUs | P4, P6, P40, P100 |
| Supported Turing GPUs | T4, RTX 6000, RTX 8000 |
| Supported Volta GPUs | V100S, V100 SXM2 |
| Supported Ampere GPUs (Compute) | H100, HGX A100, A100, A30 |
| Supported Ada GPUs (Mixed) | L40, L4, A40, A10, A16 |
A CCU license allows only one concurrent VM to be hosted per license and requires one license for each concurrent user in session-based solutions.
The total memory size for the NVIDIA A100X GPU is 80 GB HBM2e.
The board dimension for the NVIDIA L40 GPU is 10.5" × 4.4".