ONNXSpec defines arguments for configuring ONNX model serving.
Name | Type | Description | Notes |
---|---|---|---|
resources | V1ResourceRequirements | Defaults to requests and limits of 1CPU, 2Gb MEM. | [optional] |
runtime_version | str | ONNXRuntime docker image versions, default version can be set in the inferenceservice configmap | [optional] |
storage_uri | str | The URI of the exported onnx model(model.onnx) |