Turing Architecture vGPU Types#
The NVIDIA Turing architecture introduced real-time ray tracing and AI-enhanced graphics along with improved compute capabilities. Turing GPUs like the T4 are widely deployed for inference workloads, video processing, and edge AI applications, providing a proven solution for cost-effective AI Enterprise deployments.
Turing supports time-sliced vGPU configurations for flexible resource allocation in virtualized environments, making it suitable for multi-tenant GPU sharing where deterministic performance isolation isn’t required.
Turing GPU Architecture#
Physical GPUs per board: 1
The maximum number of vGPUs per board is the product of the maximum number of vGPUs per GPU and the number of physical GPUs per board.
This GPU does not support mixed-size mode.
Intended use cases:
vGPUs with more than 40 GB of framebuffer: Training Workloads
vGPUs with 40 GB of framebuffer: Inference Workloads
Required license edition: NVIDIA AI Enterprise
These vGPU types support a single display with a fixed maximum resolution.
Footnotes