Method and apparatus for scaling resources of graphics processing unit in cloud computing system
Abstract:
A method and apparatus for scaling resources of a GPU in a cloud computing system are provided. The method includes receiving requests for services from a client device, queuing the received requests in a message bus based on a preset prioritization scheme; and scaling the resources of the GPU for the requests queued in the message bus according to a preset prioritization loop.
Information query
Patent Agency Ranking
0/0