# strata-docker

Run [Strata](https://github.com/Niko1221/Strata) on an Intel Arc card under
Slackware, without installing oneAPI on the host. It wraps upstream's
documented Docker route: the SYCL engine is built and run inside the
`strata-sycl-dev` image, the setup and server run on the host. Defaults to an
Arc B580 and the Gyro-S model.

Upstream's Intel engine is experimental. Expect rough edges.

## Requirements

- Intel Arc on the `xe` (or `i915`) kernel driver, `/dev/dri/renderD128`
  usable by your user
- Docker, your user in the `docker` group
- Python 3.10+ with venv, git
- Disk: about 13 GB for the image, about 58 GB for Gyro-S
- Memory: Gyro-S needs about 21 GiB of free RAM for the expert mirror

## Usage

```sh
./strata-docker fetch     # clone Strata, check out the pinned tag (v0.2.2)
./strata-docker image     # build the strata-sycl-dev image (~6 min, 13 GB)
./strata-docker build     # build the engine for bmg-g21 (~3 min)
./strata-docker setup     # download Gyro-S and start serving
./strata-docker setup --check     # what fits, changes nothing
```

`setup` passes extra arguments to upstream's `setup.py` (e.g. `--port 8085`,
`--no-start`, `--yes`). Later runs of `setup` start the model again without
downloading.

| Variable | Default | Meaning |
|----------|---------|---------|
| `STRATA_REF` | `v0.2.2` | upstream tag or commit to check out |
| `STRATA_AOT` | `bmg-g21` | AOT target (`bmg-g31` for a Pro B70, empty for JIT on A-series) |

The server listens on `http://127.0.0.1:8080` (OpenAI API at `/v1`).

## License

Copyright (C) 2026 Danilo M. <danix@danix.xyz>

GPLv2 only. See [LICENSE](LICENSE) for the full text. Strata itself is MIT
licensed, the models carry their own licenses.

## Development Approach

This project is developed using AI-assisted tools. Code is generated with the help of AI based on human-provided specifications, design decisions, and iterative feedback.

All contributions are reviewed, tested, and curated by the maintainer before being included in the codebase. AI is used as a productivity and exploration tool, while human oversight remains central to all decisions.

The goal is to combine the flexibility of AI-assisted development with standard open-source practices such as transparency, review, and accountability.