Depending on what you're doing its taking up to 8GPUs working in parallel to ser... | Hacker News

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

		KaiserPro 14 days ago \| parent \| context \| favorite \| on: Rob Pike goes nuclear over GenAI Depending on what you're doing its taking up to 8GPUs working in parallel to serve those queries.

YetAnotherNick 14 days ago [–]

Yes but then the batch size is in 100s or even 1000s. These GPU doesn't serve just 1 user at a time.

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