Dedicated Models

Deploy Rebalance

Changed on

Start a GPU pool rebalance: move GPUs from this deployment onto another deployment you own, a target instance at a time unless concurrency raises it. A source instance is never left half-moved, so one larger target instance stops several of this deployment's at once, and one larger source instance is replaced by several target instances at once. Moving all instances stops this deployment; start it again later to resume it.

post/deploy/{deploy_id}/rebalance

Request

  • Base URL: https://api.deepinfra.com
  • URL: https://api.deepinfra.com/deploy/{deploy_id}/rebalance
  • Auth: HTTP bearer

Path parameters

deploy_idstring required

Headers

xi-api-keystring nullable
x-api-keystring nullable

Request body

target_deploy_idstring required

Deployment to grow using GPUs freed from this one.

countinteger required

Number of target instances to create.

concurrencyinteger

How many target instances may start at once (default 1). Higher finishes sooner at a deeper dip in source capacity; clamped to count. How many source instances that takes down depends on their relative size: one target instance the size of 4 source instances stops 4 of them at once, while a source instance that yields 4 target instances is always drained in one go, starting all 4.

dry_runboolean

Validate and preview without moving anything.

Response

Successful Response

replace_idstring

Id of the started rebalance; empty on a dry run.

gpustring required

GPU type being rebalanced.

source_instancesinteger required

Source instances now.

source_instances_afterinteger required

Source instances once the rebalance completes.

target_instancesinteger required

Target instances now.

target_instances_afterinteger required

Target instances once the rebalance completes.

Changes