Google Cloud Professional Machine Learning Engineer PMLE — Topic 1 Question 74

Question

You have deployed a model on Vertex AI for real-time inference. During an online prediction request, you get an “Out of Memory” error. What should you do?

Accepted Answer

Correct answer: B. The correct answer is B. Option B: Send the request again with a smaller batch of instances. Google Cloud Batch schedules and runs batch jobs at scale without managing infrastructure. This option meets the real-time / low-latency performance requirement.

Google Cloud Professional Machine Learning Engineer PMLE — Question 74