Public ROCm runtime
The package has a public, digest-pinned installation path. Dockerfile.runtime starts from vllm/vllm-openai-rocm@sha256:1fd21abe66455b4df5a2e83629e97cdcc9d58913b16052d8118b92b239792339, adds two hash-checked FLA wheels, and installs this repository's loading wrapper. It keeps the base image's ROCm PyTorch and Triton builds. The vLLM server is not used by Decision inference.
Validation boundary: the public registry manifest, base-image ancestry, package metadata and critical PyTorch binary hashes have been checked. The recipe built successfully and passed CPU imports and real AMD ROCm gfx942 GPU GPU inference for both released bundles. On the packaged three-question Choice/Noul/Score example, its complete responses matched the qualified research runtime exactly; the wrapper matched the direct engine and rejected an oversized complete input. Evidence is in runtime-build-provenance.json. This example establishes a working public installation path; it is not a full rerun of the quality or timing benchmark. Published benchmark results use the qualified runtime in each bundle's runtime.json.
Build and run
Use an AMD ROCm-compatible Linux host with Docker and the required GPU driver. Check the AMD PyTorch installation and host prerequisites. CPU and MPS inference are not supported by this model engine; no NVIDIA validation is claimed.
Run these commands from the downloaded model repository containing Dockerfile.runtime, runtime-fla-requirements.lock, pyproject.toml, src/, and the model bundle:
docker build --pull -f Dockerfile.runtime -t decision-runtime:1.0 .
mkdir -p runtime-output
docker run --rm \
--device=/dev/kfd --device=/dev/dri --group-add video --ipc=host \
-v "$PWD":/model:ro -v "$PWD/runtime-output":/output \
decision-runtime:1.0 \
python3 -m decision.example /model --local-files-only --output /output/example.json
This loads locally without a Hub token. The example tests Choice, Noul and Score through the wrapper and compares them with the frozen direct engine; inspect its actual result rather than assuming a predicted answer. Keep the runtime checks enabled. If they report a mismatch, resolve the cause before using this environment to reproduce benchmark claims. The explicit allow_unvalidated_runtime=True option is for separately labeled experiments, not benchmark reproduction.
The image is large because its public base includes the vLLM development environment. No Decision weights, dataset, user credentials or private runtime image are required to build it. Model weights are mounted at execution time.
What is pinned
The public base locks the existing OS, ROCm libraries and Python dependency environment by content digest. Its exact observed core versions are:
| Component | Observed value |
|---|---|
| Python | 3.12.13 |
| PyTorch | 2.12.0+git6bbd260 |
| PyTorch commit | 6bbd26020da1c6dc198625dfcdd968b1e4e6b1c5 |
| ROCm userspace / HIP build | 7.2.3 / 7.2.53211 |
| Triton distribution / imported version | 3.7.1+gitf0b55c07 / 3.7.1 |
| Transformers | 5.17.0 |
| Tokenizers / Safetensors | 0.23.2 / 0.8.0 |
| NumPy / Einops | 2.3.5 / 0.8.2 |
| Hugging Face Hub | 1.31.0 |
| FLA core / Flash Linear Attention | 0.5.2 / 0.5.2 |
runtime-provenance.json records the live registry manifest response, 36 shared base layers, selected actual binary SHA256 values, observed versions, wheel URLs and wheel hashes. The FLA wheels were downloaded and their SHA256 values matched the qualified overlay. runtime-fla-requirements.lock intentionally covers only that overlay; it is not a standalone dependency lock for an arbitrary system.
The official FLA installation guide separates backend PyTorch installation from FLA and documents --no-deps for pre-release/custom Torch builds. This recipe uses that boundary and never asks pip to replace Torch or Triton. Transformers is supplied by the pinned base; see its official installation documentation for the general package installation model.
Portability boundary
The public PyTorch ROCm 7.2 wheel index contains ordinary release wheels such as 2.12.0+rocm7.2. They are a different artifact from the qualified 2.12.0+git6bbd260 build and are not interchangeable evidence. The latter's source commit is public, but a source commit alone does not reproduce compiler flags, linked libraries and binary behavior.
An alternative runtime must recheck the installed versions, actual FLA Gated DeltaNet dispatch, BF16 backbone plus FP32 head, fixed prompt rendering, batch size eight, and model output agreement. Runtime changes can shift probabilities near a decision boundary even with identical weights. The supplied engine uses FLA Gated DeltaNet, reference PyTorch causal convolution and SDPA; selecting a different kernel is a new runtime configuration.