aws-samples / aws-samples/amazon-sagemaker-generativeai

Unable to invoke endpoint with djl-inference:0.33.0-lmi15.0.0-cu128

Open
#110 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
218
Forks
129
Avg merge
1m
Merged PRs (30d)
1

Description

After a successful training deploying the model using djl-inference:0.33.0-lmi15.0.0-cu128 results in the following error.

──────────────────────────────────────────────────────────────────────────────────────────────────╯
ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400)
from primary with message "{
"code": 400,
"type": "BadRequestException",
"message": "Parameter model_name is required."
}

Contributor guide

Open the contributing guide

Research direction

Start by reviewing how the model is deployed with djl-inference:0.33.0-lmi15.0.0-cu128 and how the SageMaker InvokeEndpoint request is formed. Reproduce the 400 response and trace the deployment or invocation configuration associated with the missing model_name parameter. Done means the endpoint can be invoked successfully without the reported ModelError.

Written by the indexing model from the issue text.

Assessment

Tech stack
aws
Domain
api, cloud
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.