Inference › Optimization & Performance › Performance Tuning v
disaggregated inference thoughts on dual 3090

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
disaggregated inference thoughts on dual 3090
kernelmike Offline
Member
***
Posts: 184
Threads: 23
Joined: Sep 2026
Reputation: 0
#9
10-11-2026, 07:16 PM
Good point. The pattern around small local stacks 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.
Mostly CUDA, sometimes wrong, usually measured
Find
Reply


Messages In This Thread
Re: disaggregated inference thoughts on dual 3090 - by kernelmike - 10-11-2026, 07:16 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)