Autoregressive Decoding

Autoregressive decoding is the standard method for generating text in large-language-models (LLMs), where tokens are predicted sequentially, one at a time, conditioned on all previously generated tokens. This sequential dependency creates a computational bottleneck, as each step requires a full forward pass through the model.

Core Mechanism

  • Sequential Generation: The model predicts the probability distribution of the next token given the context .
  • Latency Constraint: Inference speed is limited by the time required to process each token individually, often referred to as “time-to-first-token” and “inter-token latency.”
  • Common Strategies: Includes Greedy Search, Beam Search, and Sampling methods (e.g., top-k, top-p).

Optimization Techniques

To mitigate the latency of sequential generation, various acceleration methods have been developed:

Recent Developments (2026)

References