A vGPU is a virtual instance of a physical GPU created through virtualization software, giving a VM or container dedicated GPU compute without owning the whole card.
vGPU technology (such as NVIDIA vGPU) underpins most enterprise GPU-sharing models, letting infrastructure teams size compute to the workload rather than to the hardware.
It's typically paired with a scheduler that decides which vGPU instance gets access at any given moment.
hosted·ai's platform implements vGPU-style sharing through software-defined GPU virtualization. See the Software-Defined GPU whitepaper.
We use cookies for analytics and advertising. Privacy policy