Skip to content

docs: add Docker Model Runner usage guide for ModelPack artifacts #183

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rishi-jat wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: add Docker Model Runner usage guide for ModelPack artifacts #183

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/getting-started.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ This section lists the core infrastructure components that ModelPack is working
- **[modctl](https://github.com/modelpack/modctl)**: CLI tool for building, pushing, pulling, and managing OCI model artifacts
- **[KitOps](https://kitops.ml/)**: ModelKit packaging and deployment platform that supports the ModelPack specification
- **[AIKit](https://kaito-project.github.io/aikit/docs/packaging)**: Package AI models as OCI artifacts from local, HTTP, or Hugging Face sources with extensible formats, including ModelPack specification
- **[Docker Model Runner guide](./modelpack.md)**: Run ModelPack artifacts with Docker Model Runner using its standard pull/run workflow

### Kubernetes Integration

Expand Down
36 changes: 36 additions & 0 deletions docs/modelpack.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
# Running ModelPack Models with Docker Model Runner

This guide explains how to run CNCF ModelPack artifacts with [Docker Model Runner](https://github.com/docker/model-runner).

## What ModelPack compatibility means

Docker Model Runner includes ModelPack compatibility introduced in [docker/model-runner#516](https://github.com/docker/model-runner/pull/516).

Comment on lines +7 to +8
This allows Docker Model Runner to pull and run model artifacts that follow the ModelPack specification while keeping the normal Docker Model Runner workflow.

## Run a ModelPack model

1. Package and push a model artifact using a ModelPack-compatible tool (for example, [modctl](https://github.com/modelpack/modctl) or [AIKit](https://kaito-project.github.io/aikit/docs/packaging)).
2. Use the artifact reference from your OCI registry with Docker Model Runner.
3. Run inference with Docker Model Runner.

## Example workflow

```bash
# Example ModelPack artifact reference in an OCI registry
MODEL_REF=registry.example.com/models/my-model:v1

# Run inference via Docker Model Runner
docker model run $MODEL_REF "Hello"
```

For additional CLI and API usage, see:

- [docker/model-runner repository](https://github.com/docker/model-runner)
- [Docker Model Runner docs](https://docs.docker.com/ai/model-runner/get-started/)

## Compatibility notes

- Use a Docker Model Runner version that includes [docker/model-runner#516](https://github.com/docker/model-runner/pull/516) or newer.
- The model artifact must be a valid OCI artifact following the ModelPack specification.
- Backend/runtime-specific behavior is defined by Docker Model Runner.
Loading