NCP-AIO Installation and Deployment Practice Question
A platform engineer must validate a new NVIDIA GPU Operator deployment on a Kubernetes cluster before handing it to data scientists. Which two checks confirm that the Operator has correctly exposed GPU resources to the cluster scheduler? (Choose two.)
⚠ Common exam trap
The trap here is treating driver or runtime version matching as proof of GPU exposure instead of checking the advertised extended resource and an actual scheduled GPU pod.
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
✓
Run a CUDA-enabled pod that requests nvidia.com/gpu and verify it reaches Running state and reports the expected device.
GPU exposure is confirmed by two complementary signals: the node advertises the nvidia.com/gpu extended resource with an allocatable count matching the physical GPUs, and a test pod requesting that resource schedules successfully and can access the device. Together they validate device plugin registration and end-to-end runtime injection. Driver image tags, node runtime swaps, and DaemonSet placement on CPU-only nodes are irrelevant to this validation.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Confirm that the GPU Operator's driver DaemonSet pods are scheduled on all nodes, including CPU-only nodes.
Why it's wrong here
Driver DaemonSet pods should only run on nodes with NVIDIA GPUs, typically selected by node labels. Expecting them on CPU-only nodes is incorrect and would indicate a labeling or toleration misconfiguration. This check does not validate that GPU resources are advertised or usable by workloads.
- ✓
Run a CUDA-enabled pod that requests nvidia.com/gpu and verify it reaches Running state and reports the expected device.
Why this is correct
A scheduled pod that requests the GPU resource exercises the full path: scheduler admission, device plugin allocation, container runtime injection, and driver access inside the container. If the pod runs and nvidia-smi or a CUDA sample reports the device, the end-to-end GPU enablement is verified, not just the resource advertisement.
- ✓
Confirm that nodes advertise the nvidia.com/gpu resource and that its allocatable count matches the physical GPU count.
Why this is correct
The device plugin registers the nvidia.com/gpu extended resource with the kubelet, so each node's allocatable capacity should reflect the number of visible GPUs. Verifying this confirms the device plugin is running and has successfully discovered devices, which is a direct indicator that the scheduler can place GPU workloads on the node.
- ✗
Check that the NVIDIA driver container image tag matches the CUDA toolkit version installed in the workload image.
Why it's wrong here
The driver container version and the CUDA toolkit version in a workload image are independent concerns governed by CUDA forward compatibility rules. Requiring an exact match is not a valid validation step and could lead to unnecessary churn. This check does not demonstrate that GPU resources are exposed to the scheduler.
- ✗
Verify that the container runtime on each node has been switched from containerd to Docker with the nvidia runtime as default.
Why it's wrong here
Modern Kubernetes clusters use containerd or CRI-O with the NVIDIA container runtime configured, not Docker as the node runtime. Switching to Docker is neither required nor recommended, and it does not validate GPU resource exposure. This option reflects an outdated assumption about node runtime configuration.
About these practice questions
One of 309 original NCP-AIO practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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 NVIDIA exam blueprint
This NCP-AIO practice question is part of Courseiva's free NVIDIA 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 NCP-AIO exam.