Deployment an AI model onto a set of GPUs
| Name | Type | Description | Notes |
|---|---|---|---|
| gpuCount | Long | Number of GPUs (1-8) | |
| inferenceEngineVersion | InferenceEngineVersion | [optional] | |
| name | String | Deployment name | |
| gpuType | String | GPU type family (e.g., gpua5000, gpu3080ti) | |
| replicas | Long | Number of replicas (>=1) | |
| inferenceEngineParameters | List<String> | Optional extra inference engine server CLI args | [optional] |
| model | ModelRef |