Expand description
The inference workload spec (ADR-101 section 1) and its boundary validation.
Structs§
- Inference
Spec - An inference endpoint to adopt or run.
- Memory
Budget - Memory the instance is expected to hold (placement input).
- Serve
Args - Serve arguments. The adapter owns host and port; everything else is
mapped to the runtime’s flags or passed through
extra_args.
Enums§
- Infer
Flavor - Which server software an adapter drives.
- Latency
Class interactiveroles carry a latency bound;batchroles do not.
Constants§
- KIND_
INFERENCE - Workload kind string for inference endpoints.