Free NCP-AAI Web TestEngine Demo

Q22 Single choice

You are deploying a multi-agent customer-support system on Kubernetes using NVIDIA GPU nodes and Triton Inference Server. Traffic spikes during product launches. You need <100ms response times, zero
downtime, automatic GPU scaling, and full monitoring.

Which deployment setup best achieves cost-effective, reliable, low-latency scaling?

A
Set up one mixed GPU node pool with Cluster Autoscaler min=0, scale by network throughput, monitor
via metrics-server and logs, and skip readiness probes for fast startup.
B
Place GPU pods on on-demand nodes in one zone, disable Cluster Autoscaler, run a fixed pod count
for bursts, scale on CPU usage, and monitor with default health checks.
C
Deploy GPU pods in a node pool spanning all zones, mix GPU types, enable Cluster and Horizontal
Pod Autoscalers using Prometheus GPU and latency metrics, and monitor with NVIDIA DCGM and Grafana.
D
Use spot-instance node pools across zones, enable Cluster Autoscaler with capped nodes, scale on
memory usage, and monitor with logs and cluster events.

NCP-AAI Web TestEngine demo