Deploy a model to a workspace. The component works on compute with MSI attached.

Version: 0.0.11

Preview Internal

View in Studio: https://ml.azure.com/registries/azureml/components/deploy_model/version/0.0.11

Output of registering component

Name	Description	Type	Default	Optional	Enum
registration_details_folder	Folder containing model registration details in a JSON file named model_registration_details.json	uri_folder		True
model_id	Asset ID of the model registered in workspace/registry. Registry - azureml://registries//models//versions/ Workspace - azureml::	string		True
inference_payload	JSON payload which would be used to validate deployment	uri_file		True
endpoint_name	Name of the endpoint	string		True
deployment_name	Name of the deployment	string	default	True
instance_type	Compute instance type to deploy model. Make sure that instance type is available and have enough quota available.	string	Standard_NC24s_v3	True	['Standard_DS1_v2', 'Standard_DS2_v2', 'Standard_DS3_v2', 'Standard_DS4_v2', 'Standard_DS5_v2', 'Standard_F2s_v2', 'Standard_F4s_v2', 'Standard_F8s_v2', 'Standard_F16s_v2', 'Standard_F32s_v2', 'Standard_F48s_v2', 'Standard_F64s_v2', 'Standard_F72s_v2', 'Standard_FX24mds', 'Standard_FX36mds', 'Standard_FX48mds', 'Standard_E2s_v3', 'Standard_E4s_v3', 'Standard_E8s_v3', 'Standard_E16s_v3', 'Standard_E32s_v3', 'Standard_E48s_v3', 'Standard_E64s_v3', 'Standard_NC4as_T4_v3', 'Standard_NC6s_v2', 'Standard_NC6s_v3', 'Standard_NC8as_T4_v3', 'Standard_NC12s_v2', 'Standard_NC12s_v3', 'Standard_NC16as_T4_v3', 'Standard_NC24s_v2', 'Standard_NC24s_v3', 'Standard_NC24rs_v3', 'Standard_NC64as_T4_v3', 'Standard_ND40rs_v2', 'Standard_ND96asr_v4', 'Standard_ND96amsr_A100_v4']
instance_count	Number of instances you want to use for deployment. Make sure instance type have enough quota available.	integer	1	True
max_concurrent_requests_per_instance	Maximum concurrent requests to be handled per instance	integer	1	True
request_timeout_ms	Request timeout in ms. Max limit is 90000.	integer	60000	True
max_queue_wait_ms	Maximum queue wait time of a request in ms	integer	60000	True
failure_threshold_readiness_probe	The number of times system will try after failing the readiness probe	integer	10	True
success_threshold_readiness_probe	The minimum consecutive successes for the readiness probe to be considered successful after having failed	integer	1	True
timeout_readiness_probe	The number of seconds after which the readiness probe times out	integer	10	True
period_readiness_probe	How often (in seconds) to perform the readiness probe	integer	10	True
initial_delay_readiness_probe	The number of seconds after the container has started before the readiness probe is initiated	integer	10	True
failure_threshold_liveness_probe	The number of times system will try after failing the liveness probe	integer	30	True
timeout_liveness_probe	The number of seconds after which the liveness probe times out	integer	10	True
period_liveness_probe	How often (in seconds) to perform the liveness probe	integer	10	True
initial_delay_liveness_probe	The number of seconds after the container has started before the liveness probe is initiated	integer	10	True
egress_public_network_access	Setting it to disabled secures the deployment by restricting communication between the deployment and the Azure resources used by it	string	enabled	True	['enabled', 'disabled']

Name	Description	Type
model_deployment_details	Json file to which deployment details will be written	uri_file

azureml://registries/azureml/environments/python-sdk-v2/versions/19