Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
do you even need a vector DB here for Mistral
#11
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at speculative decoding. Once you know the plain path works, then add the faster path back in piece by piece.
Reply
#12
I tested this tonight. My result was mixed: first run looked bad, second run looked normal.
learning in public
Reply
#13
that fixed it for me too.
still benchmarking everything
Reply
#14
A couple things I'd check first. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
small models can still be good
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)