The correct first step is to profile the container's memory usage locally with memory_profiler to find the leak, then fix the code. This is because the steady memory growth despite a fixed 5 GB embedding table points to a software leak in the custom container, not a resource scaling issue—profiling locally isolates the exact object allocations causing the increase. On the Google Professional Machine Learning Engineer exam, this scenario tests your ability to distinguish between capacity planning errors and code-level bugs in Vertex AI custom containers; a common trap is immediately scaling up replicas or increasing machine memory, which masks the leak without resolving it. When debugging memory leaks in custom containers on Vertex AI, always start with local profiling tools like memory_profiler or tracemalloc before touching infrastructure. Remember the mnemonic: “Profile before provision—scale code, not hardware.”
PMLE Serving and scaling models Practice Question
This PMLE practice question tests your understanding of serving and scaling models. The scenario asks you to isolate a root cause — eliminate options that address a different problem before choosing. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
You are a machine learning engineer at a retail company. You have deployed a product recommendation model on Vertex AI Prediction using a custom container. The model is a TensorFlow SavedModel that computes embeddings using a large lookup table. The endpoint is configured with 2 replicas on n1-standard-4 (4 vCPU, 15 GB memory) machines. After deployment, you notice that the endpoint's memory usage grows over time, eventually reaching 90% and causing requests to fail with 503 errors. The container logs show no errors, but the memory usage graph shows a steady increase. The model loads the embedding table (5 GB) at startup. You suspect a memory leak. Which course of action should you take first to diagnose and resolve the issue?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue: "first"
Why it matters: Order matters here. You are being tested on which action comes before the others — not which action is generally useful.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Profile the container's memory usage locally with memory_profiler to find the leak, then fix the code.
Option A is correct because the steady memory growth despite a fixed 5 GB embedding table indicates a memory leak in the custom container code, not a capacity issue. Profiling locally with memory_profiler allows you to trace object allocations and identify the leak source before modifying the serving code, which is the most direct diagnostic step.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✓
Profile the container's memory usage locally with memory_profiler to find the leak, then fix the code.
Why this is correct
Identifies root cause for permanent fix.
Clue confirmation
The clue word "first" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
✗
Reduce the number of replicas to 1 to reduce memory contention.
Why it's wrong here
Does not address memory leak.
✗
Increase the machine memory to n1-standard-8 (30 GB).
Why it's wrong here
Delays the problem, doesn't diagnose.
✗
Restart the endpoint every hour using a Cloud Scheduler job.
Why it's wrong here
Temporary workaround, not a fix.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Google Cloud often tests the distinction between scaling up resources (Option C) and fixing the root cause (Option A), tempting candidates to choose a quick capacity increase instead of proper debugging.
Detailed technical explanation
How to think about this question
Memory leaks in TensorFlow Serving custom containers often arise from unclosed sessions, retained references to tensors, or Python objects that are not garbage-collected due to cyclic references. Using memory_profiler with mprof run or tracemalloc can pinpoint allocations that persist across inference requests. In Vertex AI, the container’s memory limit is enforced by the Kubernetes pod, and exceeding it triggers OOM kills, leading to 503 errors until the pod restarts.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A media company stores terabytes of video archives that are accessed once a year for audit purposes. Moving these objects to a cold storage tier (Azure Archive, S3 Glacier, or Google Nearline) costs a fraction of hot storage. Questions like this test whether you understand storage tiers, access frequency tradeoffs, and retrieval latency requirements.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Serving and scaling models — This question tests Serving and scaling models — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Profile the container's memory usage locally with memory_profiler to find the leak, then fix the code. — Option A is correct because the steady memory growth despite a fixed 5 GB embedding table indicates a memory leak in the custom container code, not a capacity issue. Profiling locally with memory_profiler allows you to trace object allocations and identify the leak source before modifying the serving code, which is the most direct diagnostic step.
What should I do if I get this PMLE question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Are there clue words in this question I should notice?
Yes — watch for: "first". Order matters here. You are being tested on which action comes before the others — not which action is generally useful.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
This PMLE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PMLE exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.