v2

latestOpenAPI 3.1.02026-08-07139158192.4 KB

Internal

Per-replica runtime view of a serving deployment (platform admin)

Joins each replica VM row with its pool-member state and the last scraped engine load, so an operator can see where every replica is stuck (placement, weights staging, image staging, readiness) and what traffic it is taking, without walking Nomad and Redis by hand.

get/v1/admin/inference/deployments/{id}/replicas

Path parameters

idstring required

Response

The deployment's replicas

affinityGuardUtilnumber double

prefix_affinity overflow bound; absent = the gateway default

policy'p2c_util' | 'prefix_affinity' required

The pool's member-selection policy (p2c_util when the pool row does not exist yet)

poolIdstring required

The deployment's endpoint pool id

strayMembersstring[]

Pool member hostnames no current replica owns (pending the reconcile loop's stray sweep). Usually empty.