-
Notifications
You must be signed in to change notification settings - Fork 863
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Example to demonstrate building a custom endpoint plugin #3306
Example to demonstrate building a custom endpoint plugin #3306
Conversation
```bash | ||
$ cp examples/custom_endpoint_plugin/ModelReady.java plugins/endpoints/src/main/java/org/pytorch/serve/plugins/endpoint | ||
``` | ||
Review the utilization of the [TorchServe SDK API](https://github.com/pytorch/serve/tree/master/serving-sdk) in [ModelReady.java](ModelReady.java) to implement the necessary functionality for the HTTP API endpoint. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Its not clear what this is for?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We can make this more specific and point it to the serving SDK interfaces here: https://github.com/pytorch/serve/tree/master/serving-sdk/src/main/java/org/pytorch/serve/servingsdk and also link to the corresponding implementation: https://github.com/pytorch/serve/tree/master/frontend/server/src/main/java/org/pytorch/serve/servingsdk/impl. As to why this is required, it is useful when writing a custom plugin, see the implementation in the plugin file: examples/custom_endpoint_plugin/ModelReady.java
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM Thanks!
Description
Add an example to demonstrate building a custom endpoint plugin which reports model ready status to serve inference requests.
Type of change
Feature/Issue validation/testing