Inference

Run one declared benchmark workload

Runs one cold and 1 to 32 warm iterations of a declared workload against the real engine, or of the empty harness adapter. Stores private observations locally and returns only the public field allowlist. No observation is uploaded. Device, machine, run and attempt identifiers are excluded from every response.

post/v1/benchmark/harness

Request

  • Base URL: http://localhost:9998
  • URL: http://localhost:9998/v1/benchmark/harness
  • Auth: HTTP bearer

Request body

workloadstring required

harness-floor times an empty adapter and loads no model. Any other declared workload (see GET /v1/benchmark/workloads) measures that engine family against a fixed synthetic input; the cold iteration may include the model load.

repetitionsinteger required

Response

Separate cold and warm observations, one per repetition

version1 required
osBuildstring required
appVersionstring required
buildMode'Release' | 'Debug' required
observedAtstring required
powerSource'ac' | 'battery' | 'unknown' required
lowPowerModeboolean required
thermalState'nominal' | 'fair' | 'serious' | 'critical' | 'unknown' required
provenance'measured' | 'estimated' | 'historical' | 'diagnostic' required
stage'cold' | 'warm' required
ordinalinteger required
outcome'completed' | 'incomplete' | 'cancelled' | 'failed' required
failure'cancelled' | 'adapter-error' | 'early-stop' | 'missing-statistics' | 'invalid-evidence' | 'not-run' nullable required
elapsedMsnumber required

Changes

No recorded changes to this operation across all 1 revision of this API.