Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
context size vs speed in GGUF with vLLM
#2
Good point. That matches what I saw on 4090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
2x3090 • llama.cpp • too much VRAM is still not enough
Reply


Messages In This Thread
Re: context size vs speed in GGUF with vLLM - by vrambandit - 10-13-2026, 02:33 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)