Firehose

Filtered to tagged “caching” · 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.

17 NOV 2026 · Databricks

Most reads to Lakebase Postgres are served from fast local caches, with 99.46% never leaving the compute node and 99.99999% of reads being served without hitting object storage. AI summary