Skip to content
Create Deployment Request

Create Deployment Request

Deployment an AI model onto a set of GPUs

Properties

PropertyTypeRequiredDescription
gpu-countintegeryesNumber of GPUs (1-8)
gpu-typestringyesGPU type family (e.g., gpua5000, gpu3080ti)
modelModel Refyes
namestringyesDeployment name
replicasintegeryesNumber of replicas (>=1)
inference-engine-parametersarray[string]noOptional extra inference engine server CLI args
inference-engine-versionstringnoAllowed values: 0.12.0, 0.15.1, 0.16.0, 0.17.0.
Last updated on