-
Notifications
You must be signed in to change notification settings - Fork 64
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
Ability to transform model outputs in DJL Serving #1214
Comments
cc: @chirag-orbittec |
We do have plan to allow customize output. We have a few built-in Are you considering to contribute to this feature? |
@frankfliu I can contribute that feature. We need this |
@rachitchauhan43 @chirag-orbittec We do provide a way to write your own custom input formatter https://docs.djl.ai/master/docs/serving/serving/docs/lmi/user_guides/input_formatter_schema.html and also custom output formatter https://docs.djl.ai/master/docs/serving/serving/docs/lmi/user_guides/output_formatter_schema.html Please give it a try. Closing this issue, as it was created a while ago. Feel free to open a new one, if you have any more questions. |
Description
We are using SageMaker for large model inference (LMI) as documented here
With this notebook https://github.com/deepjavalibrary/djl-demo/blob/master/aws/sagemaker/large-model-inference/sample-llm/rollingbatch_llama_7b_customized_preprocessing.ipynb, we saw there is a way to manipulate the input before it goes to then model because
parse_input
method is available as a hook but we also have a need to manipulate the output before it leaves model server.@lanking520 and @frankfliu Any thoughts on supporting that ?
Will this change the current api? How?
No. It's just an extension we are asking for.
Benefit of this will be: Users won;t have to write another service layer in front of model server just to manipulate/transform outputs.
Who will benefit from this enhancement?
References
The text was updated successfully, but these errors were encountered: