Google's TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Google's TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x (arstechnica.com)
		18 points by gmays 15 days ago \| hide \| past \| favorite \| 3 comments

redanddead 15 days ago [–]

You'd think it'd be bigger news on hn

axiologist 15 days ago | [–]

See https://news.ycombinator.com/item?id=47513475 from two days ago.

redanddead 15 days ago | | [–]

thank you sir, I missed it

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact