Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
model merge got better or just different for Kimi
#2
Good point. The pattern around prefill/decode split has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
still benchmarking everything
Reply


Messages In This Thread
Re: model merge got better or just different for Kimi - by labline - 09-22-2026, 10:29 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)