Section outline

  • June 4th, Thursday (10:30-12:30)

    LLM Inference

    • Inference
    • Model computation
    • Prefilling
    • Decoding
    • Search

    Large reasoning models

    • Introduction to large reasoning models
    • Test-time compute
    • Search against verifiers
    • Modifying proposal distribution

    References

    • Slides from the lecture

    Resources