Update a trained model deployment Added in 8.6.0

POST /_ml/trained_models/{model_id}/deployment/_update

Path parameters

  • model_id string Required

    The unique identifier of the trained model. Currently, only PyTorch models are supported.

Query parameters

  • number_of_allocations number

    The number of model allocations on each node where the model is deployed. All allocations on a node share the same copy of the model in memory but use a separate set of threads to evaluate the model. Increasing this value generally increases the throughput. If this setting is greater than the number of hardware threads it will automatically be changed to a value less than the number of hardware threads.

application/json

Body

  • number_of_allocations number

    The number of model allocations on each node where the model is deployed. All allocations on a node share the same copy of the model in memory but use a separate set of threads to evaluate the model. Increasing this value generally increases the throughput. If this setting is greater than the number of hardware threads it will automatically be changed to a value less than the number of hardware threads.

Responses

POST /_ml/trained_models/{model_id}/deployment/_update 
curl \
 -X POST http://api.example.com/_ml/trained_models/{model_id}/deployment/_update \
 -H "Content-Type: application/json" \
 -d '{"number_of_allocations":42.0}'
Request examples 
{
  "number_of_allocations": 42.0
}
Response examples (200) 
{
  "assignment": {
    "assignment_state": "started",
    "max_assigned_allocations": 42.0,
    "routing_table": {
      "*": {
        "reason": "string",
        "routing_state": "failed",
        "current_allocations": 42.0,
        "target_allocations": 42.0
      }
    },
    "": "string",
    "task_parameters": {
      "model_bytes": 42.0,
      "model_id": "string",
      "deployment_id": "string",
      "": 42.0,
      "number_of_allocations": 42.0,
      "priority": "normal",
      "queue_capacity": 42.0,
      "threads_per_allocation": 42.0
    }
  }
}