Skip to content

Models should run on NPU  #8

Description

@hrishikeshp7

Lately , using app for a few quick searches causes device to heat up very quickly and battery also drains very quick . I think this is happening because the model either runs on cpu or gpu .

I think it would be better optimised for inference on the npu especially on qualcomm devices .

Can it be done ? Or is it doable .

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions