← PDE·Google Cloud

Question 405 of 499

Operationalizing machine learning models →hardMultiple ChoiceObjective-mapped

Quick Answer

The answer is to use a machine type with multiple GPUs and configure the container to use tensor parallelism. This approach is correct because tensor parallelism splits the large language model’s layers across multiple GPUs on a single machine, allowing simultaneous computation that dramatically reduces inference time to meet a 500ms latency SLO. Unlike sharding across separate endpoints, which introduces network latency, tensor parallelism keeps communication within the high-speed GPU interconnect, making it ideal for model parallelism for LLMs on Vertex AI. On the Google Professional Data Engineer exam, this tests your understanding of Vertex AI Endpoints’ custom container capabilities and the trade-offs between intra-machine parallelism and distributed serving. A common trap is assuming that simply using more machines or TPUs is required, but the key is multi-GPU configuration within one node. Memory tip: think “tensor splits, latency fits” to remember that splitting tensors across GPUs on the same machine is the fastest path to sub-second latency.

PDE Operationalizing machine learning models Practice Question

This PDE practice question tests your understanding of operationalizing machine learning models. This is a configuration task: choose the command set that satisfies every stated requirement. Small differences — like 'secret' vs 'password' or 'transport input ssh' vs 'all' — change whether the answer is correct. 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 designing a system to serve predictions from a large language model (LLM) with a latency SLO of 500ms. The model does not fit on a single GPU and requires model parallelism. You are considering using Vertex AI Endpoints with a custom container. What additional setup is required to achieve the latency target?

Question 1hardmultiple choice

Full question →

A
Compile the model using TensorFlow XLA to optimize for single GPU execution.
Why wrong: XLA improves performance but cannot make a model that doesn't fit on one GPU fit; parallelism is required.
B
Deploy the model across multiple endpoints and use a load balancer to send requests to different parts of the model.
Why wrong: This would require splitting the model across nodes, adding network overhead and increasing latency beyond 500ms.
C
Use Vertex AI Prediction as a service for LLMs, which automatically handles hardware selection.
Why wrong: Vertex AI Prediction may not support custom LLMs with specific parallelism needs; it's for managed models.
D
Use a machine type with multiple GPUs and configure the container to use tensor parallelism.
Leveraging multiple GPUs on one node via model parallelism (e.g., tensor parallelism) is the standard approach to fit large models and meet latency.

Full breakdown with real-world context →

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Use a machine type with multiple GPUs and configure the container to use tensor parallelism.

Model parallelism across multiple GPUs on a single machine can be handled by the container using libraries like TensorFlow Distribution Strategies. Sharding across endpoints would incur network latency. Using TPUs is an alternative but not necessarily required. The key is to configure multi-GPU in the machine type.

Key principle: NAT direction and interface roles matter as much as the IP address mapping. Inside/outside designation controls which traffic is translated.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Compile the model using TensorFlow XLA to optimize for single GPU execution.
Why it's wrong here
XLA improves performance but cannot make a model that doesn't fit on one GPU fit; parallelism is required.
✗
Deploy the model across multiple endpoints and use a load balancer to send requests to different parts of the model.
Why it's wrong here
This would require splitting the model across nodes, adding network overhead and increasing latency beyond 500ms.
✗
Use Vertex AI Prediction as a service for LLMs, which automatically handles hardware selection.
Why it's wrong here
Vertex AI Prediction may not support custom LLMs with specific parallelism needs; it's for managed models.
✓
Use a machine type with multiple GPUs and configure the container to use tensor parallelism.
Why this is correct
Leveraging multiple GPUs on one node via model parallelism (e.g., tensor parallelism) is the standard approach to fit large models and meet latency.
Related concept
Static NAT maps one inside address to one outside address.

Common exam traps

Common exam trap: NAT rules depend on direction and matching traffic

NAT is not only about the public address. The inside/outside interface roles and the ACL or rule that matches traffic are just as important.

Detailed technical explanation

How to think about this question

NAT questions usually test address translation, overload/PAT behaviour, static mappings and whether the right traffic is being translated. Read the interface direction and address terms carefully.

KKey Concepts to Remember

Static NAT maps one inside address to one outside address.
PAT allows many inside hosts to share one public address using ports.
Inside local and inside global describe the private and translated addresses.
NAT ACLs identify traffic for translation, not always security filtering.

TExam Day Tips

Identify inside and outside interfaces first.
Check whether the scenario needs static NAT, dynamic NAT or PAT.
Do not confuse NAT matching ACLs with normal packet-filtering intent.

Key takeaway

NAT direction and interface roles matter as much as the IP address mapping. Inside/outside designation controls which traffic is translated.

Real-world example

How this comes up in practice

A healthcare organisation deploys an application with a public-facing web tier and a private database tier. The database subnet has no public IP and only accepts connections from the web tier's security group. Questions like this test whether you can design cloud network isolation using VNets/VPCs, subnets, and security group rules.

What to study next

Got this wrong? Here's your next step.

Review the four NAT address types (inside local, inside global, outside local, outside global), PAT port overload, and static vs dynamic NAT use cases. Then practise related PDE NAT questions on configuration and troubleshooting.

Related PDE practice-question pages

Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.

Designing data processing systems practice questions

Practise PDE questions linked to Designing data processing systems.

Building and operationalizing data processing systems practice questions

Practise PDE questions linked to Building and operationalizing data processing systems.

Operationalizing machine learning models practice questions

Practise PDE questions linked to Operationalizing machine learning models.

Ensuring solution quality practice questions

Practise PDE questions linked to Ensuring solution quality.

PDE fundamentals practice questions

Practise PDE questions linked to PDE fundamentals.

PDE scenario practice questions

Practise PDE questions linked to PDE scenario.

PDE troubleshooting practice questions

Practise PDE questions linked to PDE troubleshooting.

Practice this exam

Start a free PDE practice session

Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.

10 questions 20 questions 30 questions 50 questions Timed 30

PDE practice-test guide →Study guide →Browse all practice tests

FAQ

Questions learners often ask

What does this PDE question test?

Operationalizing machine learning models — This question tests Operationalizing machine learning models — Static NAT maps one inside address to one outside address..

What is the correct answer to this question?

The correct answer is: Use a machine type with multiple GPUs and configure the container to use tensor parallelism. — Model parallelism across multiple GPUs on a single machine can be handled by the container using libraries like TensorFlow Distribution Strategies. Sharding across endpoints would incur network latency. Using TPUs is an alternative but not necessarily required. The key is to configure multi-GPU in the machine type.

What should I do if I get this PDE question wrong?

What is the key concept behind this question?

Static NAT maps one inside address to one outside address.

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 →

How Courseiva writes practice questions · Editorial policy

Keep practising

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.

Loading comments…

This PDE 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 PDE exam.