Zenaique
Glossary · Inference

Speculative Decoding

Also known as: Assisted decoding

Use a small draft model to propose multiple tokens, then have the big model verify them in parallel.

An inference acceleration technique where a small 'draft' model proposes several tokens which the large 'target' model then verifies in parallel. Accepts the prefix that matches, rejects the rest. Roughly doubles tokens/sec with no quality change.

In practice

Shipped in vLLM, TensorRT-LLM, and llama.cpp. Senior interviews probe how the parallel verify works and why it's exact (not approximate).

Related topics

Related terms