Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
RAG chunking that actually helped with TensorRT-LLM
#3
Quote:Interesting, I hadn't tried that. That matches what I saw on 5090. Worth rechecking your defaults though, because one bad assumption can make the rest

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?
Reply


Messages In This Thread
Re: RAG chunking that actually helped with TensorRT-LLM - by northgarden37 - 10-12-2026, 07:44 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)