Can the New Model Still Use the Original API?
ModelArts supports multiple model versions and flexible traffic policies. You can use gated launch to smoothly upgrade the model version.
Prerequisites
- A service has been deployed.
- A new model version has been created by referring to Creating a New Version.
Procedure
- Log in to the ModelArts console. In the left navigation pane, choose Service Deployment > Real-Time Services. By default, the system switches to the Real-Time Services page.
- Locate the desired service and click Modify in the Operation column. The Modify Service page is displayed.
- In the Model and Configuration area, click Add Model Version and Configuration for gated launch.
Figure 1 Gated launch
- Set the traffic proportion of the two versions. Service calling requests are allocated based on the proportion. For details about other settings, see Parameter description. After the setting is complete, click Next.
- Confirm the information and click Submit.
Did this article solve your problem?
Thank you for your score!Your feedback would help us improve the website.