Avoiding power-on failures in virtualized GPUs

摘要

Various examples are disclosed for avoiding power-on failures during virtualization of graphics processing units. A computing environment can be directed to, in response to a virtual machine being powered on, identify a profile for a virtual graphics processing unit (vGPU) designated for the virtual machine, the profile specifying an amount of memory required by the vGPU, identify that the virtual machine is unable to be assigned to any of a plurality of physical graphics processing units (GPUs) based on the amount of memory required by the vGPU, free fat least the amount of memory required by the vGPU by performing a migration of at least one existing virtual machine from a first one of the physical GPUs to a second one of the physical GPUs, and assign the virtual machine to an available one of the physical GPUs and a corresponding host.