Answering While You Type: Optimizing Time-to-Answer with Streaming Generation

Abstract

Work on efficient large-language-model inference has concentrated almost entirely on reducing the cost of decoding once a request is complete. The quantity a user experiences, however, is the interval between submitting a request and receiving a usable response, and that interval can be shortened without making decoding itself faster. While a request is being composed it is already partially specified, yet conventional deployments begin no computation until submission. We propose and study streaming generation, a decoding regime in which the model begins producing a response from an incomplete request and revises it as the remaining input arrives, so that only a small residue of the answer remains to be computed once the request is submitted. We evaluate the regime on autoregressive and diffusion language models, characterise the conditions under which it reduces user-visible latency, and analyse the mechanism responsible.