Skip to content

implementation detail: LMt NLP: implement cache #12

@PtrMan

Description

@PtrMan

currently processing with LMt is slow and thus still a bit to expensive. A solution here is to cache input and result(s) on the Nim side.

TASKS

  • implement caching in Nim code

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