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

Revisions

Revisions are associated with an inference workload and represent a snapshot of its configuration. A revision is created on each change to the inference workload.

Get inference workload revisions by id.

get

Retrieve the details of inference workload revisions by workload id. Supported for clusters v2.21+.

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
workloadIdstring · uuidRequired

The Universally Unique Identifier (UUID) of the workload.

Query parameters
deletedbooleanOptional

Return only deleted resources when true.

Responses
200

Executed successfully.

application/json
get/api/v1/workloads/inferences/{workloadId}/revisions
GET /api/v1/workloads/inferences/{workloadId}/revisions HTTP/1.1
Host: app.run.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "revisions": [
    {
      "type": "runai-revision",
      "name": "very-important-job",
      "id": "123e4567-e89b-12d3-a456-426614174000",
      "workloadId": "123e4567-e89b-12d3-a456-426614174000",
      "tenantId": 1001,
      "clusterId": "71f69d83-ba66-4822-adf5-55ce55efd210",
      "projectId": 1,
      "departmentId": 2,
      "createdAt": "2022-01-01T03:49:52.531Z",
      "deletedAt": "2022-08-12T19:28:24.131Z",
      "revisionRequestedResources": {
        "gpuRequestType": "portion",
        "gpu": {
          "limit": 1.5,
          "request": 1
        },
        "gpuMemory": {
          "limit": "2G",
          "request": "200M"
        },
        "cpu": {
          "limit": 1.5,
          "request": 1
        },
        "cpuMemory": {
          "limit": "2G",
          "request": "200M"
        },
        "extendedResources": [
          {
            "resource": "hardware-vendor.example/foo",
            "quantity": 2,
            "exclude": false
          }
        ]
      },
      "podsRequestedResources": {
        "gpuRequestType": "portion",
        "gpu": {
          "limit": 1.5,
          "request": 1
        },
        "gpuMemory": {
          "limit": "2G",
          "request": "200M"
        },
        "cpu": {
          "limit": 1.5,
          "request": 1
        },
        "cpuMemory": {
          "limit": "2G",
          "request": "200M"
        },
        "extendedResources": [
          {
            "resource": "hardware-vendor.example/foo",
            "quantity": 2,
            "exclude": false
          }
        ]
      },
      "requestedPods": {
        "number": 1,
        "min": 2,
        "max": 5,
        "parallelism": 3,
        "completions": 5
      },
      "requestedNodePools": [
        "default"
      ],
      "allocatedResources": {
        "gpu": 1.5,
        "gpuMemory": "200Mi",
        "cpu": 0.5,
        "cpuMemory": "0B",
        "extendedResources": [
          {
            "resource": "hardware-vendor.example/foo",
            "quantity": 2,
            "exclude": false
          }
        ]
      },
      "currentNodePools": [
        "default"
      ],
      "runningPods": 1,
      "images": [
        "alpine:latest"
      ],
      "environmentVariables": {
        "ANY_ADDITIONAL_PROPERTY": "text"
      },
      "command": "sleep",
      "arguments": "1000",
      "conditions": [
        {
          "type": "Ready",
          "status": "False",
          "message": "Resource validation failed: ...",
          "reason": "ErrorConfig",
          "lastTransitionTime": "2022-01-01T03:49:52.531Z"
        }
      ],
      "phase": "Creating",
      "phaseMessage": "Not enough resources in the requested nodepool",
      "phaseUpdatedAt": "2022-06-08T11:28:24.131Z",
      "additionalFields": {
        "ANY_ADDITIONAL_PROPERTY": "anything"
      }
    }
  ]
}

Get inference workload revisions count.

get

Retrieve the number of an inference workload revisions from a cluster. Supported for clusters v2.21+.

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
workloadIdstring · uuidRequired

The Universally Unique Identifier (UUID) of the workload.

Query parameters
deletedbooleanOptional

Return only deleted resources when true.

Responses
200

Executed successfully.

application/json
countinteger · int64RequiredExample: 1
get/api/v1/workloads/inferences/{workloadId}/revisions/count
GET /api/v1/workloads/inferences/{workloadId}/revisions/count HTTP/1.1
Host: app.run.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "count": 1
}

Get revision data.

get

Retrieve revision details using a revision id. Supported for clusters v2.21+.

Authorizations
AuthorizationstringRequired

Bearer authentication

Path parameters
revisionIdstring · uuidRequired

The Universally Unique Identifier (UUID) of the revision.

Responses
200

Executed successfully.

application/json
typestringRequiredExample: runai-revision
namestringRequiredExample: very-important-job
idstring · uuidRequired
workloadIdstring · uuidRequired
tenantIdinteger · int32Required

The id of the tenant.

Example: 1001
clusterIdstring · uuidRequired

The id of the cluster.

Example: 71f69d83-ba66-4822-adf5-55ce55efd210
projectIdstringRequired

The id of the project.

Example: 1Pattern: .*
departmentIdstring · min: 1Required

The id of the department.

Example: 2Pattern: .*
createdAtstring · date-timeRequiredExample: 2022-01-01T03:49:52.531Z
deletedAtstring · date-time · nullableOptionalExample: 2022-08-12T19:28:24.131Z
requestedNodePoolsstring[]OptionalExample: default
currentNodePoolsstring[]OptionalExample: default
runningPodsinteger · int32OptionalExample: 1
imagesstring[]OptionalExample: alpine:latest
commandstringOptionalExample: sleep
argumentsstringOptionalExample: 1000
phasestring · enumRequiredPossible values:
phaseMessagestringOptionalExample: Not enough resources in the requested nodepool
phaseUpdatedAtstring · date-timeOptionalExample: 2022-06-08T11:28:24.131Z
get/api/v1/workloads/inferences/revisions/{revisionId}
GET /api/v1/workloads/inferences/revisions/{revisionId} HTTP/1.1
Host: app.run.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "type": "runai-revision",
  "name": "very-important-job",
  "id": "123e4567-e89b-12d3-a456-426614174000",
  "workloadId": "123e4567-e89b-12d3-a456-426614174000",
  "tenantId": 1001,
  "clusterId": "71f69d83-ba66-4822-adf5-55ce55efd210",
  "projectId": 1,
  "departmentId": 2,
  "createdAt": "2022-01-01T03:49:52.531Z",
  "deletedAt": "2022-08-12T19:28:24.131Z",
  "revisionRequestedResources": {
    "gpuRequestType": "portion",
    "gpu": {
      "limit": 1.5,
      "request": 1
    },
    "gpuMemory": {
      "limit": "2G",
      "request": "200M"
    },
    "cpu": {
      "limit": 1.5,
      "request": 1
    },
    "cpuMemory": {
      "limit": "2G",
      "request": "200M"
    },
    "extendedResources": [
      {
        "resource": "hardware-vendor.example/foo",
        "quantity": 2,
        "exclude": false
      }
    ]
  },
  "podsRequestedResources": {
    "gpuRequestType": "portion",
    "gpu": {
      "limit": 1.5,
      "request": 1
    },
    "gpuMemory": {
      "limit": "2G",
      "request": "200M"
    },
    "cpu": {
      "limit": 1.5,
      "request": 1
    },
    "cpuMemory": {
      "limit": "2G",
      "request": "200M"
    },
    "extendedResources": [
      {
        "resource": "hardware-vendor.example/foo",
        "quantity": 2,
        "exclude": false
      }
    ]
  },
  "requestedPods": {
    "number": 1,
    "min": 2,
    "max": 5,
    "parallelism": 3,
    "completions": 5
  },
  "requestedNodePools": [
    "default"
  ],
  "allocatedResources": {
    "gpu": 1.5,
    "gpuMemory": "200Mi",
    "cpu": 0.5,
    "cpuMemory": "0B",
    "extendedResources": [
      {
        "resource": "hardware-vendor.example/foo",
        "quantity": 2,
        "exclude": false
      }
    ]
  },
  "currentNodePools": [
    "default"
  ],
  "runningPods": 1,
  "images": [
    "alpine:latest"
  ],
  "environmentVariables": {
    "ANY_ADDITIONAL_PROPERTY": "text"
  },
  "command": "sleep",
  "arguments": "1000",
  "conditions": [
    {
      "type": "Ready",
      "status": "False",
      "message": "Resource validation failed: ...",
      "reason": "ErrorConfig",
      "lastTransitionTime": "2022-01-01T03:49:52.531Z"
    }
  ],
  "phase": "Creating",
  "phaseMessage": "Not enough resources in the requested nodepool",
  "phaseUpdatedAt": "2022-06-08T11:28:24.131Z",
  "additionalFields": {
    "ANY_ADDITIONAL_PROPERTY": "anything"
  }
}
PreviousInferencesNextDistributed

Last updated