For the complete documentation index, see llms.txt. This page is also available as Markdown.

Inferences

Inference workloads deploy trained models into a production environment to generate predictions from live data. These workloads are prioritized over Trainings and Workspaces during scheduling. NVIDIA Run:ai Inference workloads support auto-scaling to maintain service-level agreements (SLAs) by dynamically adjusting resources as demand changes.

Create an inference.

post

Create an inference using container related fields.

Authorizations
AuthorizationstringRequired

Bearer authentication

Body
and
and
Responses
202

Request completed successfully.

application/json
and
post/api/v1/workloads/inferences

Get inference data.

get

Retrieve inference details using a workload id.

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
workloadIdstring · uuidRequired

The Universally Unique Identifier (UUID) of the workload.

Responses
200

Executed successfully.

application/json
and
get/api/v1/workloads/inferences/{workloadId}

Delete an inference.

delete

Delete an inference using a workload id.

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
workloadIdstring · uuidRequired

The Universally Unique Identifier (UUID) of the workload.

Responses
202

Accepted.

application/json
codeinteger · min: 100 · max: 599Required
messagestringRequired
delete/api/v1/workloads/inferences/{workloadId}

Update inference spec.

patch

Update the specification of an existing inference workload.

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
workloadIdstring · uuidRequired

The Universally Unique Identifier (UUID) of the workload.

Body

The specifications of the inference to be updated.

Responses
202

Executed successfully.

application/json
and
patch/api/v1/workloads/inferences/{workloadId}

Get inference metrics data.

get

Retrieve inference metrics data by id. Supported from control-plane version 2.18 or later.

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
workloadIdstring · uuidRequired

The Universally Unique Identifier (UUID) of the workload.

Query parameters
startstring · date-timeRequired

Start date of time range to fetch data in ISO 8601 timestamp format.

Example: 2023-06-06T12:09:18.211Z
endstring · date-timeRequired

End date of time range to fetch data in ISO 8601 timestamp format.

Example: 2023-06-07T12:09:18.211Z
numberOfSamplesinteger · max: 1000Optional

The number of samples to take in the specified time range.

Default: 20Example: 20
Responses
200

Executed successfully.

get/api/v1/workloads/inferences/{workloadId}/metrics

Get inference pod's metrics data.

get

Retrieve inference metrics pod's data by workload and pod id. Supported from control-plane version 2.18 or later.

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
workloadIdstring · uuidRequired

The Universally Unique Identifier (UUID) of the workload.

podIdstring · uuidRequired

The requested pod id.

Query parameters
startstring · date-timeRequired

Start date of time range to fetch data in ISO 8601 timestamp format.

Example: 2023-06-06T12:09:18.211Z
endstring · date-timeRequired

End date of time range to fetch data in ISO 8601 timestamp format.

Example: 2023-06-07T12:09:18.211Z
numberOfSamplesinteger · max: 1000Optional

The number of samples to take in the specified time range.

Default: 20Example: 20
Responses
200

Executed successfully.

get/api/v1/workloads/inferences/{workloadId}/pods/{podId}/metrics

Last updated