AWS · AIP-C01
Application performance
AIP-C01 · Lesson 19 of 23 · 2:34:56
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the AIP-C01 exam (AWS Certified Generative AI Developer - Professional). In this lesson: responsive systems with pre-computation, latency-optimized inference, parallel calls, and streaming, retrieval and throughput tuning, temperature, top-p, and top-k per task, A/B tests, resource allocation from token patterns, auto scaling, profiling, and vector query optimization. Includes three original practice questions.
Preview the topics
- A product comparison calls three models one after the other, and each call takes two seconds, although none of them depends on the others. How can AnyCompany cut the wait most?
- AnyCompany’s product tagging feature returns slightly different tags each time for the same product, and the catalog team wants consistent results. Which setting should change?
- Every morning at nine, traffic to AnyCompany’s SageMaker AI endpoint triples within minutes, and the first requests time out while new instances start. What should the team configure?