Skip to content

[Feature] Improve AI Model Caching #49

@maximedogawa

Description

@maximedogawa

User Story

As a user
I want that the most common used models are cached and hold in memory with Ollama
So that I can benefit from faster model reply circles.

Description

the most common used model should stay in the memory cache of Ollama so that fast replies can be used. normally Ollama has to load the model in memory and the model stays for a time in memory. most common used models should stay in memory for a longer time so that fast replies can be enabled. also improve model caching effectiveness.

Acceptance Criteria

  • add model caching capabilities

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions