EXexoscale
deployment

Create Deployment

Changed on

Deploy a model on an inference server

post/ai/deployment

Request

Request body

gpu-countinteger required

Number of GPUs (1-8)

inference-engine-version'0.12.0' | '0.15.1' | '0.16.0' | '0.17.0' | '0.18.0' | '0.18.1' | '0.19.0' | '0.19.1' | '0.20.0' | '0.20.1' | '0.20.2' | '0.21.0' | '0.22.0' | '0.22.1' | '0.23.0' | '0.24.0' | '0.25.0' | '0.25.1' | '0.26.0'

Inference engine version

namestring required

Deployment name

gpu-typestring required

GPU type family (e.g., gpua5000, gpu3080ti)

product-namestring

Billing identifier for this deployment. Used by the Router for usage counters and Kafka events.

replicasinteger required

Number of replicas (>=1)

inference-engine-parametersstring[]

Optional extra inference engine server CLI args

Response

OK

idstring uuid

Operation ID

reason'incorrect' | 'unknown' | 'unavailable' | 'forbidden' | 'busy' | 'fault' | 'partial' | 'not-found' | 'interrupted' | 'unsupported' | 'conflict'

Operation failure reason

messagestring

Operation message

state'failure' | 'pending' | 'success' | 'timeout'

Operation status

Changes

  • 63da6f74c845Revision changes
    • warning

      removed the optional property from the response with the status

    • warning

      removed the optional property from the response with the status

    • warning

      removed the optional property from the response with the status

    • warning

      removed the optional property from the response with the status

    • info

      added the new optional request property

    • info

      the request property default value changed from 0.17.0 to 0.26.0

    • info

      added the new 0.18.0 enum value to the request property

    • info

      added the new 0.18.1 enum value to the request property

    • info

      added the new 0.19.0 enum value to the request property

    • info

      added the new 0.19.1 enum value to the request property

    • info

      added the new 0.20.0 enum value to the request property

    • info

      added the new 0.20.1 enum value to the request property

    • info

      added the new 0.20.2 enum value to the request property

    • info

      added the new 0.21.0 enum value to the request property

    • info

      added the new 0.22.0 enum value to the request property

    • info

      added the new 0.22.1 enum value to the request property

    • info

      added the new 0.23.0 enum value to the request property

    • info

      added the new 0.24.0 enum value to the request property

    • info

      added the new 0.25.0 enum value to the request property

    • info

      added the new 0.25.1 enum value to the request property

    • info

      added the new 0.26.0 enum value to the request property

    • info

      added the non-success response with the status

  • e05707a7b346Revision changes
    • breaking

      the request property became required

    • breaking

      the request property became required

    • breaking

      the request property became required

    • breaking

      the request property's min was increased to 1.00

    • breaking

      the request property's min was increased to 1.00

    • warning

      removed the optional property from the response with the status

    • info

      api tag deployment added

    • info

      api tag dedicated-inference removed

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the non-success response with the status

    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status

    • info

      added the required property to the response with the status

    • info

      added the required property to the response with the status

    • info

      added the required property to the response with the status

    • info

      added the required property to the response with the status