Sign in
latestOpenAPI 3.1.02026-08-17151182241.7 KB

7e2fe85577f4

Internal

Mint the next generation of a serving deployment (platform admin)

Server-side "next generation from this one": every spec field in the body overrides the source, every absent field is inherited, and the result is created as a weight-0 green in the source's lane. Structural overrides (organizationId, publicModelId, nodePool) are rejected: they would make a different lane or tenant. A delta touching only routing or sizing fields is also rejected, naming PATCH or /scale, because no new replicas are needed and a new generation would be waste. The new green and its lane lock are written in one transaction, so two simultaneous revises of one lane cannot both become green. The response carries the field diff and the rollout capacity warning for running both generations at once.

post/v1/admin/inference/deployments/{id}/revise

Path parameters

idstring required

Request body

changeCausestring

Why this revision exists. Stored on the row and shown in the revision history.

dtypestring
enginestring
engineImagestring
envobject
extraArgsstring[]
gpuCountPerReplicainteger
gpuModelIdstring
maxConcurrencyPerReplicainteger
maxModelLeninteger
maxPromptBytesinteger
minPromptBytesinteger
nativeFamiliesstring[]
nodePoolstring

Structural: rejected. A different node pool is a different lane.

organizationIdstring

Structural: rejected. A different org is a different tenant.

publicModelIdstring

Structural: rejected. A different model is a different lane.

quantizationstring
replicaRuntime'' | 'vm' | 'pod'

Changing the runtime is a replica-class change like any other, so it rolls out rather than mutating in place.

replicasDesiredinteger
replicasMaxinteger
replicasMininteger
servedModelIdstring
versionstring

Rollout tag for the new generation: the low-cardinality version metric label the gateway reports, which is what separates the two sides of the roll. ABSENT CLEARS IT rather than inheriting the source's, because a green carrying blue's tag registers the identical label and collapses both sides into one series. Cleared, the green reports as "green" against blue's "blue". Present sets it explicitly.

weightsRefstring

Response

The new generation

laneCommittedGpusinteger

GPUs the target lane's existing live deployments already commit for this GPU model.

rolloutOkboolean

Whether rolloutPeakGpus fits the serving budget. A WARNING, not a blocker: running a tight rollout and draining the old side as the new one ramps is a legitimate plan.

rolloutPeakGpusinteger

Peak GPU demand while the rollout is in flight: the new generation's footprint plus laneCommittedGpus, because both generations hold real hardware until the old one is drained.

rolloutReasonstring

Why the rollout peak does not fit, in lane terms, when rolloutOk is false