BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//OneJoy//events//EN
BEGIN:VEVENT
UID:onejoy-event-108340@onejoy
DTSTAMP:20261116T065327Z
DTSTART:20261124T230000Z
DTEND:20261125T010000Z
SUMMARY:Vector Compression & Mem/Stg Economics: FP16 Vectors\, and Matryoshka Embeddings
LOCATION:
DESCRIPTION:The single biggest issue with adopting vector search\, despite its many benefits\, is the cost of running it at scale. As vector dimensions and the datasets needed for them grow\, the memory footprint\, cache pressure\, and storage bandwidth all start to increase. This talk examines vector search from a storage-first and systems engineering perspective\, focusing on how representation directly impacts performance\, cost\, and retrieval quality.\n\nWe start by understanding the basics of vector search\, the\nhttps://onejoy.io/event/108340
URL:https://onejoy.io/event/108340
END:VEVENT
END:VCALENDAR