Technique

Speculative Decoding

Acceleration where a tiny draft model proposes tokens that the main model verifies in parallel.

Definition

Speculative decoding pairs a fast small draft model with the target model. The draft emits several tokens; the target verifies all of them in a single forward pass and rolls back where it disagrees. The result is 2–3× faster inference with identical outputs.

Common use cases

  • Latency reduction
  • Cost reduction
  • vLLM/TGI optimisation

Related terms

    Speculative Decoding — AI Glossary | Railwail