Updating a Model Deployment with a Burstable VM

Follow these steps to update a model deployment with a burstable instance.

• Console
• CLI
• API

• 1. From the model deployments page, select the name of the model deployment to update. If you need help finding the list of model deployments, see Listing Model Deployments.
  2. Select Update model deployment to update the configuration.
  3. Edit the model deployment as needed.
  4. Under Select compute, select Change shape.
  5. In the Compute panel, select Burstable.
  6. (Optional) In Burstable utilization per OCPU, select the baseline OCPU utilization percentage.
     This value is the percentage of OCPU you expect to use most often.

     Note
     
     For model deployments, only the value of 50% is supported.
  7. Select Submit.

• Use the oci data-science model-deployment update command and required parameters to edit (update) a model deployment.

  For example, update a deployment with:

  Copy

  oci data-science model-deployment update \
  --model-deployment-id <MODEL_DEPLOYMENT_OCID>
  --model-deployment-configuration-details file://<MODEL_DEPLOYMENT_CONFIGURATION_FILE>

  Then use this model deployment JSON configuration file for update:

  {
    "modelDeploymentConfigurationDetails": {
      "deploymentType": "SINGLE_MODEL",
      "modelConfigurationDetails": {
        "modelId": "ocid1.datasciencemodel.oc1.iad........",
        "instanceConfiguration": {
          "instanceShapeName": "VM.Standard.E4.Flex",
          "modelDeploymentInstanceShapeConfigDetails": {
            "ocpus": 1,
            "memoryInGBs": 16,
            "cpuBaseline": "BASELINE_1_2"
          }
        },
        "scalingPolicy": {
          "policyType": "FIXED_SIZE",
          "instanceCount": 1
        },
        "bandwidthMbps": 10
      },
      "environmentConfigurationDetails" : {
        "environmentConfigurationType": "OCIR_CONTAINER",
        "image": "iad.ocir.io/testtenancy/image_name:1.0.0",
        "entrypoint": [
          "python",
          "/opt/entrypoint.py"
        ],
        "serverPort": "5000",
        "healthCheckPort": "5000"
      },
      "streamConfigurationDetails": {
        "inputStreamIds": null,
        "outputStreamIds": null
      }
    }
  }

  For a complete list of parameters and values for CLI commands, see the CLI Command Reference.

• Use the UpdateModelDeployment operation to edit (update) a model deployment.

  For example:

  endpoint = (
      endpoint = "https://datascience.us-ashburn-1.oci.oraclecloud.com/20190101/modelDeployments/ocid1.datasciencemodeldeployment.oc1.iad.amaaaabggsfewffgew/"
  )
   
  config = oci.config.from_file(profile_name="OC1")
  config["region"] = "us-ashburn-1"
  token_file = config.get("security_token_file", None)
  signer = None
  if token_file:
      with open(token_file, "r", encoding="UTF-8") as file:
          token = file.read()
      private_key = oci.signer.load_private_key_from_file(config.get("key_file", ""))
      signer = oci.auth.signers.SecurityTokenSigner(token, private_key)
   
  model_deployment_details_payload = {
      "projectId": "ocid1.datascienceproject.oc1.eu-milan-1.amaaaaaabbbcccccc",
      "modelDeploymentConfigurationDetails": {
          "deploymentType": "SINGLE_MODEL",
          "modelConfigurationDetails": {
              "modelId": "ocid1.datasciencemodel.oc1.iad.amaaaaaav66vvniatytp7xjhid3inftgo52j55ozlm7hzglvvqni5wxi3bja",
              "scalingPolicy": {
                  "instanceCount": 1,
                  "policyType": "FIXED_SIZE"
              },
          "instanceConfiguration": {
              "instanceShapeName": "VM.Standard.E4.Flex",
              "modelDeploymentInstanceShapeConfigDetails": {
                  "ocpus": 1,
                  "memoryInGBs": 8,
                  "cpuBaseline": "BASELINE_1_2"
          }
        }
      },
          "modelId": "ocid1.datasciencemodel.oc1.iad.amaaaabggsfewffgew",
          "bandwidthMbps": 10,
          },
      },
      "compartmentId": "ocid1.compartment.oc1..gegwgsefvrhresafwo",
  }
   
  update_response = requests.put(
      endpoint, auth=signer, json=model_deployment_details_payload
  )
  print(update_response.text)