In a virtualized environment that is powered by NVIDIA graphics cards, the NVIDIA virtual GPU (vGPU) software is installed on the virtualization layer along with the hypervisor. This software creates virtual GPUs that allow each virtual machine (VM) to share the physical GPU installed on the server. For more demanding calculations, one virtual machine can use the performance of several physical GPUs at the same time.
NVIDIA vGPU software includes a graphics or compute driver for each virtual machine. As the processes that used to be calculated on the CPU are transferred to the GPU, users get much better performance. In virtualized and cloud environments, GPUs can handle demanding engineering and graphics applications, as well as computationally intensive tasks such as AI and data science.