Docker

uv build --wheel                   # the image installs this wheel
docker compose up --build          # needs the NVIDIA Container Toolkit and a GPU host
curl http://127.0.0.1:8000/health  # answers once the first start has fetched the checkpoint

Needs a GPU host with the NVIDIA Container Toolkit: taken verbatim from the repository's tested docs, run record runs/2026-10-01_docker-first-gpu-start/.

• The image is vLLM's 0.30.0 release image, pinned by digest, plus the decisio wheel with its serve extra; the build argument APPLY_PATCHES=1 adds the patch series (off by default).
• The first start downloads the checkpoint into the decisio-data volume, mounted at /data; it is never part of the image.
• The container runs as a non-root user, and compose publishes the port on 127.0.0.1 only.
• The entrypoint starts the server with --model "${DECISIO_MODEL:-Qwen/Qwen3.6-35B-A3B-FP8}" and --model-class hidden-readout, listening on DECISIO_HOST and DECISIO_PORT; arguments after the image name are passed to the server.
• It checks for an NVIDIA GPU first and exits with an explanation when the container cannot see one.
• Release images go to ghcr.io/aminry/decisio, with their digest in the release notes; to run one instead of building, replace build: in compose.yaml with image: ghcr.io/aminry/decisio@sha256:<digest>.
• Dockerfile and compose.yaml explain the rest.

First GPU start (2026-10-01, one RTX PRO 6000 Blackwell, the image built on the machine from the Dockerfile): healthy in 651 s including the checkpoint download and in 206 s from the cached volume, and the README's example request and the conformance gates C2 to C4 pass against the container (runs/2026-10-01_docker-first-gpu-start/). The image published with v0.1.0 repeated the start from its digest: healthy in 223 s with the checkpoint cached, example and conformance passing (pushed_image_0.1.0/ in the same record). The image has been started on a GPU with the Qwen base only.