Quick Answer
The correct choice is to build a custom container image that includes the CUDA runtime library, because the error 'ImportError: libcudart.so.11.0: cannot open shared object file' directly indicates that the CUDA runtime library version 11.0 is absent from the container environment. When a custom prediction routine (CPR) depends on a native library requiring CUDA, the shared object must be present at runtime; a prebuilt Vertex AI serving container often lacks specific CUDA versions, so you must extend or rebuild the image to include the exact runtime. On the Google Professional Machine Learning Engineer exam, this scenario tests your understanding of custom container requirements for GPU-accelerated inference, and a common trap is trying to install the library via a startup script or pip—those run too late, after the native library is loaded. Remember the memory tip: "CUDA in the build, not at runtime" to avoid import errors.
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.
A team deploys a model on Vertex AI that uses a custom prediction routine (CPR) with a dependency on a native library. The container crashes with 'ImportError: libcudart.so.11.0: cannot open shared object file'. How should they resolve this?
Build a custom container image that includes the CUDA runtime library.
Ensures the library is available.
Submit the model for batch prediction to avoid the error.
Why wrong: Error would still occur in batch.
Request a GPU machine type for the endpoint.
Why wrong: GPU does not fix missing library.
Use a Vertex AI pre-built container for PyTorch instead.
Why wrong: May not include the specific library version.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Build a custom container image that includes the CUDA runtime library.
The error 'ImportError: libcudart.so.11.0: cannot open shared object file' indicates that the CUDA runtime library (version 11.0) is missing from the container environment. Since the custom prediction routine (CPR) depends on a native library that requires this CUDA runtime, the correct solution is to build a custom container image that includes the CUDA runtime library. This ensures the shared object is available at runtime, resolving the import error.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Build a custom container image that includes the CUDA runtime library.
Why this is correct
Ensures the library is available.
Related concept
Read the scenario before looking for a memorised answer.
Submit the model for batch prediction to avoid the error.
Why it's wrong here
Error would still occur in batch.
Request a GPU machine type for the endpoint.
Why it's wrong here
GPU does not fix missing library.
Use a Vertex AI pre-built container for PyTorch instead.
Why it's wrong here
May not include the specific library version.
Common exam traps
Google Cloud often tests the misconception that requesting a GPU machine type automatically provides the necessary CUDA libraries, but in reality, the CUDA runtime must be explicitly included in the container image, as the GPU machine type only provides the hardware and driver, not the user-space libraries.
Detailed technical explanation
Under the hood, the CUDA runtime library (libcudart.so) is a shared object that provides the CUDA driver API and runtime functions. When a native library is compiled against a specific CUDA version (e.g., 11.0), it expects that exact version's libcudart.so to be present in the LD_LIBRARY_PATH. In Vertex AI, custom prediction routines run inside a container; if the base image lacks the required CUDA runtime, the dynamic linker fails. Building a custom container with the correct CUDA toolkit version ensures the shared object is available, and the container can be deployed to either CPU or GPU endpoints as needed.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
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
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Serving and scaling models — study guide chapter
Learn the concepts, then practise the questions
Serving and scaling models practice questions
Targeted practice on this topic area only
All PMLE questions
506 questions across all exam domains
Google Professional Machine Learning Engineer study guide
Full concept coverage aligned to exam objectives
PMLE practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise PMLE questions linked to Scaling prototypes into ML models.
Practise PMLE questions linked to Automating and orchestrating ML pipelines.
Practise PMLE questions linked to Collaborating within and across teams to manage data and models.
Practise PMLE questions linked to Architecting low-code ML solutions.
Practise PMLE questions linked to Collaborating to manage data and models.
Practise PMLE questions linked to Serving and scaling models.
Practise PMLE questions linked to Monitoring ML solutions.
Practise PMLE questions linked to Solving business challenges with ML.
Practise PMLE questions linked to PMLE fundamentals.
Practise PMLE questions linked to PMLE scenario.
Practise PMLE questions linked to PMLE troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Serving and scaling models — This question tests Serving and scaling models — Read the scenario before looking for a memorised answer..
The correct answer is: Build a custom container image that includes the CUDA runtime library. — The error 'ImportError: libcudart.so.11.0: cannot open shared object file' indicates that the CUDA runtime library (version 11.0) is missing from the container environment. Since the custom prediction routine (CPR) depends on a native library that requires this CUDA runtime, the correct solution is to build a custom container image that includes the CUDA runtime library. This ensures the shared object is available at runtime, resolving the import error.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
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 →
Last reviewed: Jun 30, 2026
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.