Vertical Pod Autoscaler (VPA)
The following is an example on how to use VPA with the MLOps Python client:
vpa_spec = mlops.DeployVpaResourceSpec(
cpu=mlops.DeployVpaResourceBounds(
unit="CORES",
max=2,
min=1
),
memory=mlops.DeployVpaResourceBounds(
unit="GIB",
max=3,
min=2
)
)
deployment = mlops.DeployDeployment(
display_name="shady-mlops-client-deployment-test-2",
description="shady-mlops-client-deployment-test-2",
project_id=projects[0].id ,
# monitor_disable=True,
security=mlops.DeploySecurity(
passphrase=mlops.DeployAuthenticationPassphrase(
hash="this is a new plain-text",
passphrase_hash_type=mlops.DeployPassphraseHashType.PLAINTEXT
)
),
deployment_environment_id=environments[0].id,
single_deployment=mlops.DeploySingleDeployment(
deployment_composition=deployment_composition,
kubernetes_resource_spec=mlops.DeployKubernetesResourceSpec(
kubernetes_resource_requirement=mlops.DeployKubernetesResourceRequirement(
requests={
"cpu": "500m",
"memory": "350Mi"
},
),
replicas=1,
),
vpa_spec=vpa_spec
),
custom_cors= mlops.DeployCors(
origins= ["http://localhost:8888/notebooks/mlops_client_basic.ipynb"]
)
)
Feedback
- Submit and view feedback for this page
- Send feedback about H2O MLOps to cloud-feedback@h2o.ai