Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
on-device inference worth the effort with llama.cpp
#2
Quote:Posting this in case it saves someone else a little time.

Tried to reproduce it just now. On B200 with PyTorch, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
Reply


Messages In This Thread
Re: on-device inference worth the effort with llama.cpp - by marbleyard32 - 10-17-2026, 06:55 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)