Home › GCP ML Engineer › cloudcomputing › mleserving › Which ML model-optimisation technique should an …
Which ML model-optimisation technique should an ML Engineer use to REDUCE inference latency + memory footprint for a trained model — referenced in PMLE §4.2?
AQuantisation (and pruning + distillation) of the trained model
BIncreasing model size before serving
CCloud Memorystore
DCloud DNS
Answer & Solution
Correct answer: A. Quantisation (and pruning + distillation) of the trained model
Quantisation / pruning / distillation shrink the serving model (per PMLE §4.2 simplification techniques). The other options don't optimise.
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 Vertex AI deployment option should an ML Engineer choose for a HIGH-THROUGHPUT onlinWhich 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