You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In this article, learn about deployment of [MLflow](https://www.mlflow.org) models to Azure Machine Learning for both real-time and batch inference, and about the different tools you can use to manage the deployment.
22
+
In this article, learn about deployment of [MLflow](https://www.mlflow.org) models to Azure Machine Learning for both real-time and batch inference, and about different tools you can use to manage the deployment.
23
23
24
24
## No-code deployment
25
25
@@ -72,7 +72,7 @@ Azure Machine Learning also supports deploying models to both online and batch e
72
72
The following table shows the input types supported by the MLflow built-in server versus Azure Machine Learning online endpoints.
73
73
74
74
| Input type | MLflow built-in server | Azure Machine Learning online endpoints |
75
-
| :- | :-: | :-: |
75
+
|---| :-: | :-: |
76
76
| JSON-serialized pandas DataFrames in the split orientation |**✓**|**✓**|
77
77
| JSON-serialized pandas DataFrames in the records orientation | Deprecated ||
78
78
| CSV-serialized pandas DataFrames |**✓**| Use batch inferencing. For more information, see [Deploy MLflow models to batch endpoints](how-to-mlflow-batch.md). |
@@ -228,11 +228,11 @@ Azure Machine Learning offers the following tools to deploy MLflow models to onl
228
228
Each tool has different capabilities, particularly for which type of compute it can target. The following table shows the support for different MLflow deployment scenarios.
229
229
230
230
| Scenario | MLflow SDK | Azure Machine Learning CLI/SDK or studio |
231
-
|---|---|---|---|
232
-
| Deploy to managed online endpoints<sup>1</sup> |[Progressive rollout of MLflow models to online endpoints](how-to-deploy-mlflow-models-online-progressive.md)|
231
+
|---| :-: | :-: |
232
+
| Deploy to managed online endpoints<sup>1</sup> |[Progressive rollout of MLflow models to online endpoints](how-to-deploy-mlflow-models-online-progressive.md)|[Deploy MLflow models to online endpoints](how-to-deploy-mlflow-models-online-endpoints.md)|
233
233
| Deploy to managed online endpoints with a scoring script | Not supported<sup>3</sup> |[Customize MLflow model deployments](how-to-deploy-mlflow-models-online-endpoints.md#customize-mlflow-model-deployments)|
234
234
| Deploy to batch endpoints | Not supported<sup>3</sup> |[Use MLflow models in batch deployments](how-to-mlflow-batch.md)|
235
-
| Deploy to batch endpoints with a scoring script | Not supported<sup>3</sup> |[Customize model deployment with scoring script](how-to-mlflow-batch.md#customize-model-deployment-with-scoring-script)|
235
+
| Deploy to batch endpoints with a scoring script | Not supported<sup>3</sup> |[Customize model deployment with scoring script](how-to-mlflow-batch.md#customize-model-deployment-with-scoring-script)|
236
236
| Deploy to web services like Azure Container Instances or Azure Kubernetes Service (AKS) | Legacy support<sup>2</sup> | Not supported<sup>2</sup> |
237
237
| Deploy to web services like Container Instances or AKS with a scoring script | Not supported<sup>3</sup> | Legacy support<sup>2</sup> |
0 commit comments