Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
quant support gaps: what are you seeing?
#11
A couple questions before I guess too hard. Are you testing this on B200 or something else?
Reply
#12
Quote:Need a little more detail here. Is this local-only or are you routing anything externally?

Good point. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Mostly CUDA, sometimes wrong, usually measured
Reply
#13
My first guess would be this: If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Reply


Forum Jump:


Users browsing this thread: 2 Guest(s)