Start a trained model deployment Added in 8.0.0
It allocates the model to every machine learning node.
Path parameters
-
The unique identifier of the trained model. Currently, only PyTorch models are supported.
Query parameters
-
cache_size number | string
The inference cache size (in memory outside the JVM heap) per node for the model. The default value is the same size as the
model_size_bytes
. To disable the cache,0b
can be provided. -
deployment_id string
A unique identifier for the deployment of the model.
-
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.
-
priority string
The deployment priority.
Values are
normal
orlow
. -
queue_capacity number
Specifies the number of inference requests that are allowed in the queue. After the number of requests exceeds this value, new requests are rejected with a 429 error.
-
threads_per_allocation number
Sets the number of threads used by each model allocation during inference. This generally increases the inference speed. The inference process is a compute-bound process; any number greater than the number of available hardware threads on the machine does not increase the inference speed. 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.
-
timeout string
Specifies the amount of time to wait for the model to deploy.
-
wait_for string
Specifies the allocation status to wait for before returning.
Values are
started
,starting
, orfully_allocated
.
curl \
-X POST http://api.example.com/_ml/trained_models/{model_id}/deployment/_start
{
"assignment": {
"adaptive_allocations": {
"enabled": true,
"min_number_of_allocations": 42.0,
"max_number_of_allocations": 42.0
},
"assignment_state": "started",
"max_assigned_allocations": 42.0,
"reason": "string",
"routing_table": {
"*": {
"reason": "string",
"routing_state": "failed",
"current_allocations": 42.0,
"target_allocations": 42.0
}
},
"": "string",
"task_parameters": {
"": 42.0,
"model_id": "string",
"deployment_id": "string",
"number_of_allocations": 42.0,
"priority": "normal",
"queue_capacity": 42.0,
"threads_per_allocation": 42.0
}
}
}