Skip to main content
T5 Others iFlytek New grad

iFLYTEK Feixing AI Infra campus hiring

Real iFLYTEK AI Infra campus hiring interview questions covering inference optimization and related topics

Inference optimization

Inference optimization

  1. What hardware optimizations does NVIDIA GPU provide specifically for FP8?
  2. How do the two FP8 formats (E4M3 and E5M2) differ, and how is each computed?
  3. How do you compute KV Cache size when storing in FP8?
  4. How do H-series and L-series GPUs differ in architecture?
  5. Which recent techniques or methods in inference optimization are worth watching?