Skip to main content
T1 Large companies and unicorns Kuaishou Internship Round 1

Kuaishou AI Infra internship first round (2)

Real Kuaishou AI Infra internship first-round interview questions covering inference optimization and operator optimization

Inference optimization Operator optimization

Theory

  1. What is the PagedAttention mechanism in vLLM? How is Chunked Prefill implemented? What is Continuous Batching, and what does it do?

Project deep dive

  1. Which concrete methods did operator optimization in the inference framework use?
  2. What was the design and build idea for the Memory Pool?
  3. How was the framework test plan designed? How large was the test data?

Live coding

  1. Given a 2D array where each row is sorted, find the Kth smallest element.