25 lines
1.2 KiB
Markdown
25 lines
1.2 KiB
Markdown
# Model fleet policy
|
|
|
|
Domovoy does not equate intelligence with GPU, model name, or provider kind.
|
|
Hardware and endpoint identity are operational observations only. A model is
|
|
eligible for routing only after the existing qualification and activation
|
|
gates pass.
|
|
|
|
`FAST`, `MEDIUM`, and `HEAVY` are capability service classes, not hardware
|
|
claims. A CPU model may be the best available quality model, and a GPU model
|
|
may be unavailable, degraded, or unrated.
|
|
|
|
The Capability owner derives a provider-neutral `ModelRating` from evidence:
|
|
|
|
- `QUALITY`: high measured quality and zero critical failures;
|
|
- `BALANCED`: supported model with usable quality/reliability evidence;
|
|
- `FAST`: supported model whose observed latency is strong enough for quick work;
|
|
- `UNRATED`: discovery or incomplete evidence; it cannot be promoted by name.
|
|
|
|
The score combines quality, reliability, latency and evidence coverage. Missing
|
|
measurements remain explicit. A model can change category after a new immutable
|
|
qualification/performance revision. The current CPU route is an operational
|
|
choice, not a permanent hardware assumption. CPU is preferred in the current
|
|
deployment; if it is unavailable, the policy tries another ready class before
|
|
using the Lifeboat recovery path.
|