Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You fine-tuned a Llama-2 7B model in Azure AI Foundry and registered it. The operations team must run the model completely offline on a factory IoT gateway that runs Azure IoT Edge on Ubuntu 22.04 with an NVIDIA T4 GPU. Updates must be delivered as versioned container images pulled from Azure Container Registry. Which deployment method meets the requirements?

  • Create an Azure Container Apps revision with a bring-your-own-model image and move the container to the gateway using docker save and load commands.

  • Package the model with the Foundry containerization CLI to generate a GPU-enabled Docker image, push the image to Azure Container Registry, and deploy it as an Azure IoT Edge module that uses the nvidia runtime.

  • Publish the model as a managed online endpoint in Azure Machine Learning and configure the gateway to call the endpoint over a NAT connection.

  • Export the model parameters to Azure OpenAI and access the GPT endpoint from the gateway.

Microsoft Azure AI Engineer Associate AI-102
Implement generative AI solutions
Your Score:
Settings & Objectives
Random Mixed
Questions are selected randomly from all chosen topics, with a preference for those you haven’t seen before. You may see several questions from the same objective or domain in a row.
Rotate by Objective
Questions cycle through each objective or domain in turn, helping you avoid long streaks of questions from the same area. You may see some repeat questions, but the distribution will be more balanced across topics.

Check or uncheck an objective to set which questions you will receive.

Wipe Score
Bash, the Crucial Exams Chat Bot
AI Bot