nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #330

You work as an ML researcher at an investment bank, and you are experimenting with the Gemma large language model (LLM). You plan to deploy the model for an internal use case. You need to have full…

The correct answer is B. Deploy the model on a Google Kubernetes Engine (GKE) cluster by using the deployment options. Deploying the Gemma LLM on a GKE cluster using Model Garden deployment options gives you full control over the underlying infrastructure while benefiting from optimized configurations. This setup minimizes inference time through fine-tuned resource allocation and allows…

Submitted by naveen.iyer· Apr 18, 2026ML pipeline operationalization

Question

You work as an ML researcher at an investment bank, and you are experimenting with the Gemma large language model (LLM). You plan to deploy the model for an internal use case. You need to have full control of the mode's underlying infrastructure and minimize the model's inference time. Which serving configuration should you use for this task?

Options

  • ADeploy the model on a Vertex AI endpoint manually by creating a custom inference container.
  • BDeploy the model on a Google Kubernetes Engine (GKE) cluster by using the deployment options
  • CDeploy the model on a Vertex AI endpoint by using one-click deployment in Model Garden.
  • DDeploy the model on a Google Kubernetes Engine (GKE) cluster manually by cresting a custom

How the community answered

(35 responses)
  • A
    9% (3)
  • B
    71% (25)
  • C
    14% (5)
  • D
    6% (2)

Explanation

Deploying the Gemma LLM on a GKE cluster using Model Garden deployment options gives you full control over the underlying infrastructure while benefiting from optimized configurations. This setup minimizes inference time through fine-tuned resource allocation and allows customization of the serving environment, which is ideal for internal, performance-sensitive use cases.

Topics

#ML Model Deployment#LLM Serving#Google Kubernetes Engine (GKE)#Infrastructure Control

Community Discussion

No community discussion yet for this question.

Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice