Deployment Service
Add a deployment adapter
Attaches a LoRA adapter to a deployment. If the deployment is at adapter capacity, force can evict the oldest adapter.
Authorization
bearerAuth AuthorizationBearer <token>
In: header
Path Parameters
projectId*string
Project identifier.
endpointId*string
Endpoint identifier.
deploymentId*string
Deployment identifier.
Request Body
application/json
Configuration for attaching a LoRA adapter to a deployment that has adapter loading enabled.
adapterModelId*string
Adapter model identifier to attach.
adapterRevisionId?string
Optional adapter revision to pin. If omitted, the latest revision is resolved at request time.
force?boolean
Whether to evict the oldest adapter if the deployment is at adapter capacity.
Response Body
application/json
application/json
curl -X POST "https://example.com/projects/string/endpoints/string/deployments/string/adapters" \ -H "Content-Type: application/json" \ -d '{ "adapterModelId": "string" }'{ "adapterModelId": "string", "desiredRevisionId": "string", "perCluster": [ { "adapterModelId": "string", "clusterId": "string", "realizedRevisionId": "string", "realizedEtag": "string", "state": "ADAPTER_LOAD_STATE_PENDING", "reason": "string", "message": "string", "readyPodCount": 0, "failedPodCount": 0, "totalPodCount": 0, "loadedAt": "2019-08-24T14:15:22Z", "updatedAt": "2019-08-24T14:15:22Z", "adapterModel": "string", "realizedRevision": "string" } ], "etag": "string", "adapterModel": "string", "desiredRevision": "string"}