Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
speculative decoding in llama.cpp
#11
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly.
small models can still be good
Reply


Messages In This Thread
Re: speculative decoding in llama.cpp - by quantsupply - 10-14-2026, 04:11 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)