DocsRun it
CPU stand-in for development
Serve every route from a small model on the CPU, to build against the API anywhere.
The stand-in serves the same routes from a small model, so you can develop and test a client without a card. It is not the measured system, and its answers are not for measurement.
Figure · The stand-in
Every route, from a small model on the CPU, so you can build against the API anywhere.
- uv sync --extra dev --frozeninstall with the development tools
- uv run pytestthe unit tests, on any machine
- --backend hfevery route, from
Qwen/Qwen3-0.6B-Baseon the CPU - for developmentnot the measured system; its answers are not for measurement
CI runs the stand-in on a pinned revision of the model, and the commands on these pages that it can serve are run against it.
Source: docs/running.md "CPU stand-in for development" at the pinned release.
uv sync --extra dev --frozenuv run pytestuv run python -m decisio.serve.vllm_engine --backend hf --model Qwen/Qwen3-0.6B-BaseRun against the CPU stand-in at v0.11.1 on 2026-10-14: the install and the server start; the unit tests passed in decisio's own CI on this commit.
The commands on these pages that the stand-in can serve are run against it.
| Word | Meaning |
|---|---|
| stand-in | --backend hf: every route, from Qwen/Qwen3-0.6B-Base on the CPU |
| unit tests | uv run pytest, which runs on any machine; the GPU tests need a card |
What it is, and is not
Section titled “What it is, and is not”uv sync --extra dev --frozenuv run pytestuv run python -m decisio.serve.vllm_engine --backend hf --model Qwen/Qwen3-0.6B-BaseRun against the CPU stand-in at v0.11.1 on 2026-10-14: the install and the server start; the unit tests passed in decisio's own CI on this commit.
uv run pytestruns the unit tests on any machine; the GPU tests (pytest -m gpu) need a card, and run by hand until a nightly GPU runner is registered.--backend hfserves every route from a small Hugging Face model on the CPU, for developing and testing the routes; it is not the measured system and its answers are not for measurement.- CI runs the stand-in on
Qwen/Qwen3-0.6B-Baseat a pinned revision (STAND_IN_REVISIONin.github/workflows/ci.yml). examples/tasks/walks through task registration against it.
What next
Section titled “What next”- Get started: send a first question to it.
- Teach it your question: the walk-through that runs on a laptop against the stand-in.
- Choose your machine: the paths that run the real bases.