Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefill bottlenecks on longer prompts: anyone testing this?
#2
A couple things I'd check first. On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
Mostly CUDA, sometimes wrong, usually measured
Reply


Messages In This Thread
Re: prefill bottlenecks on longer prompts: anyone testing this? - by kernelmike - 09-13-2026, 02:57 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)