GENERATIVE-AI-ENGINEER-ASSOCIATE · Question #101
GENERATIVE-AI-ENGINEER-ASSOCIATE Question #101: Real Exam Question with Answer & Explanation
The correct answer is D: Deploy the model using provisioned throughput as it comes with performance guarantees. Deploying the model using provisioned throughput is the best option when expecting high incoming request volumes. Provisioned throughput offers performance guarantees, ensuring that the application can handle the expected load without encountering issues like rate limiting or slo
Question
A Generative AI Engineer developed an LLM application using the pay-per-token Foundation Model API. Now that the application is ready to be deployed, they would like to ensure the model endpoint can serve high incoming volumes of requests in production. What should the Generative AI Engineer consider?
Options
- ASwitch to using External Models instead
- BThrottle the incoming batch of requests manually to avoid rate limiting issues
- CChange to a model with a fewer number of parameters in order to reduce hardware constraint
- DDeploy the model using provisioned throughput as it comes with performance guarantees
Explanation
Deploying the model using provisioned throughput is the best option when expecting high incoming request volumes. Provisioned throughput offers performance guarantees, ensuring that the application can handle the expected load without encountering issues like rate limiting or slow response times. This option allows the application to scale efficiently and provides consistent service quality in production.
Topics
Community Discussion
No community discussion yet for this question.