Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
do you even need a vector DB here on B200
#11
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at long context. Not glamorous advice, but repeatable baselines save a lot of time.
curious and caffeinated
Reply
#12
My first guess would be this: On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Reply
#13
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
Reply
#14
Ran a quick check on my box. On Threadripper box with MLX, I saw basically the same behavior. I expected the model choice to matter more than it did.
Apple Silicon • MLX mostly
Reply
#15
Interesting, I hadn't tried that. I ended up in about the same place using PyTorch. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)