mediumMultiple Choice
PDE Practice Question: A data science team wants to deploy a model that…
A data science team wants to deploy a model that requires a custom container with specific NVIDIA CUDA version. They build the image and push to Artifact Registry. When deploying to Vertex AI, the model fails to load with an error: 'Failed to start container: invalid ELF header'. What is the most likely cause?
⚠ Common exam trap
The trap is focusing on CUDA or model file issues, but the ELF header error specifically points to architecture mismatch.
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
✓
The container image was built for a different CPU architecture (e.g., ARM64) than the Vertex AI machine (x86_64)
The error 'invalid ELF header' indicates that the container image's executable format is not compatible with the host architecture. Vertex AI uses x86_64 machines, so if the image was built for ARM64 (e.g., on an Apple M1), it will fail to start. This is the most likely cause. Other options would produce different errors (e.g., CUDA incompatibility, permission denied, corrupted model file).
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
The container image was built for a different CPU architecture (e.g., ARM64) than the Vertex AI machine (x86_64)
Why this is correct
An ELF header mismatch means the binary's architecture does not match the host's. Building on ARM64 (for example, an Apple silicon laptop) produces ARM64 executables, which Vertex AI's x86_64 machines cannot load. Rebuilding the image with `--platform linux/amd64` resolves the failure.
- ✗
The model file (saved as .pkl) is corrupted
Why it's wrong here
A corrupted .pkl file triggers a deserialisation or unpickling error inside the running process, after the container has started successfully. It is tempting because model artefacts do get corrupted, and re-uploading the file would fix that, but the ELF header error concerns the container's executable binary, not the model.
- ✗
The CUDA version in the container is incompatible with the GPU on the machine
Why it's wrong here
A CUDA mismatch surfaces as runtime errors such as 'no kernel image is available' or a CUDA driver version warning once the container starts, not 'invalid ELF header' at container start. It is tempting because the stem stresses a specific CUDA version, and matching CUDA to the GPU is genuinely required for GPU workloads.
- ✗
The container does not have the necessary permissions to access the model file in Cloud Storage
Why it's wrong here
Storage permissions produce HTTP 403 or access-denied errors when reading the model, not an ELF header failure, which occurs before the process starts. It is tempting because Cloud Storage access is a common deployment fault, and granting the Vertex AI service account objectViewer would be correct if the error were a permission denial.
Go deeper
Related to this question
About these practice questions
Courseiva writes every PDE question from scratch — 747 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
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.