Skip to content

First-class local inference #9

Description

@rlnorthcutt

Problem statement

Ollama ships in the container, but there's no real path to using it: GPU access into the container isn't guaranteed, container memory may need to scale for the model in use, and there's no guide for running a local model and making it usable across all decks.

What success looks like

A user can run a local model in the shipped container with GPU access working, sized memory, and clear documentation for making it available across every deck.

Impacted repositories

  • omnideck
  • site

Acceptance criteria

  • The container reliably gets GPU access when available.
  • Container memory can be sized appropriately for the local model in use.
  • A published guide covers running a local model and exposing it across decks.

Related

  • See the separate Research item on tuning llama.cpp/Ollama for speed and larger models (MoE offload, etc.) — that informs this epic but isn't a sub-issue of it.

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

    roadmapTier 1 item — triggers auto-add to the org project

    Type

    Projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions