Research

Research seriesL2algorithms

The Math Behind Modern LLM Inference

The algorithms that make a large language model answer on demand — attention and the KV cache, speculative decoding, quantization error, and vector-index recall — derived properly, with the complexity and the point where each one breaks. Grounded in the primary papers.

Murali Chillakuru·1 articles
  1. 1
    Attention and the KV Cache: The Arithmetic of a Forward Pass

    Why serving a language model is a memory problem, derived from the attention equation to the exact bytes a running conversation holds.