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 dist-epoch

4 days ago

After you load the weights into the GPU and keep the KV cache there too, you don't need any other significant traffic.

1 comment

dist-epoch

Reply

numpad0  4 days ago

Even in tensor parallel modes? I thought it could only work if you're fine stalling all but n GPU for n users at any given moments.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities