Create a LoRAAdapter in a namespace

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Path Params
string
required

Kubernetes namespace of the resource.

Body Params

LoRAAdapter represents a LoRA adapter produced by a FineTuningJob.
Adapters are stored under a per-model layout in SeaweedFS
(/loraadapters/{namespace}/{model}/{adapter-name}) and can be
dynamically loaded into a running ModelDeployment via the vLLM
load/unload endpoints.

tags here and on Model use the Go 1.24 encoding/json "omitzero" form. Every
other v1alpha1 type uses "omitempty". Verify generated CRD OpenAPI matches
expectations under both; if not, switch to omitempty for consistency.

string

APIVersion defines the versioned schema of this representation of an object.
Servers should convert recognized schemas to the latest internal value, and
may reject unrecognized values.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources

string

Kind is a string value representing the REST resource this object represents.
Servers may infer this from the endpoint the client submits requests to.
Cannot be updated.
In CamelCase.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds

metadata
object
spec
object
required

spec defines the desired state of LoRAAdapter

Responses

400

Bad Request — the request body or parameters are invalid.

401

Unauthorized — no or invalid bearer token provided.

403

Forbidden — the authenticated principal lacks permission.

409

Conflict — a resource with the same name already exists.

422

Unprocessable Entity — the object failed schema validation.

Language
Credentials
Bearer
URL
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json