turbopuffer(@turbopuffer):we're redesigning our caching tier current: whole files evicted in the order written (FIFO) new: smaller chunks, least-read evicted first (LFU) on a cluster where a small fraction of data gets most of the reads, this improves byte hit ratio by ~2x → p99 query latency drops ~2x

turbopuffer

@turbopuffer

{vector, full-text} search engine built on object storage. fast, cheap, trillion scale. powers Anthropic, Harvey, Notion, Cognition, and more

가입 October 2023

6 팔로잉 중 17.8K 팬

turbopuffer@turbopuffer

2026.10.30 16:08

we're redesigning our caching tier current: whole files evicted in the order written (FIFO) new: smaller chunks, least-read evicted first (LFU) on a cluster where a small fraction of data gets most of the reads, this improves byte hit ratio by ~2x → p99 query latency drops ~2x