AI inference glossary
Serving

Speculative decoding

Also known as spec decode, draft-and-verify decoding

In plain English

Speculative decoding lets a cheaper helper draft several tokens ahead, then asks the full model to approve them together instead of generating each one separately.

Technical definition

Speculative decoding proposes several future tokens cheaply and verifies them together with the target model, reducing the number of expensive serial decode steps.

Engineering details

A draft model or built-in prediction heads generate candidates. The target model evaluates those candidates in a batched verification pass and accepts the valid prefix without changing the target distribution when the algorithm is implemented exactly.

Why it matters

The speedup depends on how many draft tokens are accepted and on the cost of drafting and verification. Dense and MoE models can behave differently because verifying several positions may activate more expert weights.

How to read it in InferenceX

Compare speculative recipes at realistic acceptance rates and verify model quality. InferenceX distinguishes MTP-enabled and disabled curves because the benefit changes across concurrency and interactivity.