Answer-first summary for fast verification
Answer: Create a local web service deployment configuration and deploy the model to a local Docker container.
The correct answer is D because deploying the model to a local Docker container using LocalWebservice allows for iterative debugging without redeployment. This approach enables modifying the entry script and reloading the service using service.reload(), which is not possible with AKS or ACI deployments. The community discussion strongly supports D with high upvotes (e.g., 50 upvotes) and references to Azure documentation, emphasizing that local deployment simplifies troubleshooting. Options A and B involve redeployment to cloud services, violating the 'no redeployment' requirement. Option C suggests adding a breakpoint and redeploying to AKS, which still requires redeployment. Option E involves registering a new model version, which doesn't address iterative code debugging without redeployment.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You have deployed a model to an Azure Kubernetes Service (AKS) inference cluster, but the deployment failed due to an error in the entry script. You need to debug the error by iteratively modifying the code and reloading the service without redeploying it for each update. What should you do?
A
Modify the AKS service deployment configuration to enable application insights and re-deploy to AKS.
B
Create an Azure Container Instances (ACI) web service deployment configuration and deploy the model on ACI.
C
Add a breakpoint to the first line of the entry script and redeploy the service to AKS.
D
Create a local web service deployment configuration and deploy the model to a local Docker container.
E
Register a new version of the model and update the entry script to load the new version of the model from its registered path.
No comments yet.