Skip to content

Is there a pure GPU inference version available? #90

Description

@904557558

The current version of TEN-VAD runs less efficiently on GPUs than it does on CPUs. This may be attributed to the fact that certain operators do not support GPU computation, resulting in a hybrid CPU/GPU processing mode.
Are there any plans to develop a pure-GPU version? This would be critically important for scenarios involving high-concurrency, multi-user detection.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions