client.models.update_processing_engines

Update processing engineprocessing engine - Processing engines are infrastructure units that run models. The total amount of processing engines purchased define the account’s overall parallel processing capacity. To check the processing engines current status, get processing details. Modzy provides the capability to granularly manage the job completion speed for each model-version. You can set model readiness and autoscaling for each individual model-version in your account. Each processing engine deploys a single model-version instance and runs one input at a time. Inputs are run in parallel the same amount of times as the amount of processing engines set and started for that model-version. For example, if a job is submitted to run 4 inputs through a model that has 2 processing engines, 2 inputs get processed at the same time. When a processing engine finishes running an input, it picks up the next input in the queue.s

client.models.update_processing_engines(model, version, min_engines, max_engines, timeout = 0, poll_rate = 5)

Updates the minimum and maximum processing engines for a specific model identifier and version

Parameters

Parameter

Type

Description

Example

model

str
Model

A model identifier assigned by Modzy or a preloaded model object.

'ed542963de'

version

str

The model’s version number. It follows the semantic versioning format.

'0.0.1'

min_engines

int

The minimum number of processing engines a model’s version can run. It is a positive integer or 0.

0

max_engines

int

The maximum number of processing engines a model’s version can run. It is a positive integer or 0. max_engines must be >= min_engines.

1

timeout

int

Time in seconds to wait until processing engine is spun up. 0 means return immediately, 'None' means block and wait forever. Defaults to 0, which means no wait.

120

poll_rate

int

If timeout is nonzero, this value will determine the rate at which the state of the cluster is checked. Defaults to 5.

10

Examples

>>>client.models.update_processing_engines('ed542963de', '0.0.27', 1, 1)
>>>version = client.models.get_version('ed542963de', '0.0.27')
>>>version.processing.minimum_parallel_capacity
1

Did this page help you?