Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
speculative decoding actually worth it for Qwen
#7
Quote:Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, no

A couple questions before I guess too hard. What model, what runtime, and roughly what context size?
measure twice, benchmark three times
Reply


Messages In This Thread
Re: speculative decoding actually worth it for Qwen - by cacheline - 10-17-2026, 04:27 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)