Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library
← Back to context

Comment by Readerium

12 hours ago

LLMs are memory bandwidth bound not compute bound.

3 comments

Readerium

Reply

AntiUSAbah  9 hours ago

LLMs are bound by both and depends on the hardware which factor is higher.

ondra  11 hours ago

This is incorrect, prompt processing is compute bound.

icelancer  10 hours ago

This is only true for some parts of the time cost function.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities