aws-samples / aws-samples/amazon-sagemaker-generativeai
Unable to invoke endpoint with djl-inference:0.33.0-lmi15.0.0-cu128
- 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
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