matreche/modelarts-umn
1
0
Fork 0
forked from docs/modelarts
Code Issues Pull Requests Packages Projects Releases Wiki Activity
modelarts-umn/umn/source/model_deployment/introduction_to_model_deployment.rst
otcbot[bot] 2d9d363ec9
Update content (#29) 
Changes to ma_umn from doc-exports#1


This is an automatically created Pull Request for changes to ma_umn in opentelekomcloud-docs/doc-exports#1.
Please do not edit it manually, since update to the original PR will overwrite local changes.
Original patch file, as well as complete rst archive,  can be found in the artifacts of the opentelekomcloud-docs/doc-exports#1

Reviewed-by: kucerakk <kucerakk@gmail.com>
2022-05-09 12:59:46 +00:00

672 B
Raw Blame History

original_name

modelarts_23_0058.html

Introduction to Model Deployment

After a training job is complete and a model is generated, you can deploy the model on the Service Deployment page. You can also deploy the model imported from OBS. ModelArts supports the following deployment types:

  • Real-Time Services <modelarts_23_0060>

    Deploy a model as a web service to provide real-time test UI and monitoring capabilities.

  • Batch Services <modelarts_23_0066>

    A batch service can perform inference on batch data. After data processing is complete, the batch service automatically stops.