Workloads V2

The Workloads V2 API allows you to create, retrieve, and delete workloads that originate from third-party ML frameworks, tools, or the broader Kubernetes ecosystem. These workloads are registered in the platform through the Workload Types API, some are already registered in NVIDIA Run:ai, while others can be added by administrators. Each submission combines the user’s Kubernetes manifest with NVIDIA Run:ai scheduling metadata, enabling consistent orchestration, monitoring, and governance. See Extending workload supportarrow-up-right for more details.

Create a workload. [Experimental]

post

Submit a workload with metadata and a Kubernetes manifest.

Authorizations
AuthorizationstringRequired

Bearer authentication

Body
manifestBase64Encodedstring · byteOptional

Kubernetes YAML manifest encoded in base 64. Mutually exclusive with manifest.

Example: YXBpVmVyc2lvbjogdjEKa2luZDogUG9kCm1ldGFkYXRhOgogIG5hbWU6IG15LXBvZApzcGVjOgogIGNvbnRhaW5lcnM6CiAgLSBuYW1lOiBuZ2lueAogICAgaW1hZ2U6IG5naW54OmxhdGVzdAo=
Responses
post
/api/v2/workloads

Get a specific workload. [Experimental]

get

Retrieve details of a specific workload by ID

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
WorkloadV2Idstring · uuidRequired

The ID of the workload.

Responses
chevron-right
200

Successfully retrieved the workload

application/json
get
/api/v2/workloads/{WorkloadV2Id}

Delete a workload. [Experimental]

delete

Delete a specific workload by ID

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
WorkloadV2Idstring · uuidRequired

The ID of the workload.

Responses
delete
/api/v2/workloads/{WorkloadV2Id}

Last updated