Firehose

Filtered to Papers, tagged “sequential decoding” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

18 NOV 2026 · Paper

This paper proposes a new decoding strategy for looped language models, called late entry, which allows the model to skip initial passes and directly use a deep context cache, resulting in faster decoding times. Practitioners might care about this approach because it could lead to significant speedups in applications where decoding speed is crucial.