Executing a Machine-Trained Model using Selectively Streamed Model Weights

    公开(公告)号:US20240296373A1

    公开(公告)日:2024-09-05

    申请号:US18116282

    申请日:2023-03-01

    CPC classification number: G06N20/00

    Abstract: A technique implements a machine-trained model using resources of a local system. The technique operates by successively obtaining portions of model weights on an as-needed basis. The local system obtains at least some of the portions by downloading them from a source system in a streaming operation. The technique further successively executes parts of the machine-trained model in the local system using the portions of model weights that have been obtained, to provide an output result. An entirety of the model weights used by the local system to provide the output result is less than an entirety of the model weights available for download at the source system. The technique enables the local system to locally execute the machine-trained model without overburdening its local resources, and with reduced consumption of network resources.

Patent Agency Ranking