Constrained Decoding
Restricting which tokens a model may emit at each step.
Обзор
Constrained decoding masks the logits so only tokens consistent with a grammar, schema or regular expression remain possible. It solves the problem that asking for valid output produces valid output most of the time, and a pipeline cannot be built on most of the time. It exists because enforcement during generation removes the need for retries and repair logic afterwards.
Граф технологий
Как Constrained Decoding связана с остальным стеком.