Home › GCP ML Engineer › cloudcomputing › mleserving › Which Vertex AI deployment option should an ML E…
Which Vertex AI deployment option should an ML Engineer choose for a HIGH-THROUGHPUT online endpoint that needs GPU acceleration?
AVertex AI online endpoint with a GPU-attached machine type + appropriate autoscaling
BCPU-only endpoint with no autoscaling
CCloud Memorystore
DCloud DNS
Answer & Solution
Correct answer: A. Vertex AI online endpoint with a GPU-attached machine type + appropriate autoscaling
GPU-attached Vertex AI endpoints + autoscaling handle GPU-served high-throughput (per PMLE §4.2). The others aren't suitable.
Related questions
Which GCP service should an ML Engineer use to serve a model directly inside BigQuery as aWhich Vertex AI capability should an ML Engineer use to serve XGBoost / LightGBM / scikit-Which GCP-compatible streaming runtime should an ML Engineer use to MAKE PREDICTIONS over Which Vertex AI feature should an ML Engineer use to deploy a CUSTOM container that wraps Which ML model-optimisation technique should an ML Engineer use to REDUCE inference latencWhich Vertex AI Feature Store capability should an ML Engineer use to FETCH a feature vectWhich Vertex AI endpoint type should an ML Engineer recommend to keep model traffic INSIDEWhich Vertex AI feature should an ML Engineer use to run an A/B test between two model ver