Inference › Inference Engines › Other Engines v
prefill bottlenecks on longer prompts on A6000

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
prefill bottlenecks on longer prompts on A6000
vrambandit Offline
Member
***
Posts: 168
Threads: 14
Joined: Sep 2026
Reputation: 0
#2
10-18-2026, 11:41 PM
Thanks, that helps. That matches what I saw on B200. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
2x3090 • llama.cpp • too much VRAM is still not enough
Find
Reply


Messages In This Thread
Re: prefill bottlenecks on longer prompts on A6000 - by vrambandit - 10-18-2026, 11:41 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)