Skip to main content
T3 Chips and hardware Moore Threads Internship Round 2

Moore Threads AI Infra internship second round

Real Moore Threads AI Infra internship second-round interview questions covering inference and operator optimization

Inference optimization Operator optimization

Below is what the Moore Threads AI Infra internship second round covered.

Project experience

  1. Deep follow-ups on the project

Quantization focus

  1. Describe the concrete flows of INT8 quantization and W4A16 quantization, and when each applies
  2. Scenario: if the data distribution is extremely uneven (min = -10000, other values clustered in [-1, 1]), which quantization scheme should you choose?

Coding

  1. Hand-write a CUDA operator (plain-text environment, no highlighting or autocomplete)