Inference › Optimization & Performance › Benchmarks v
adapter stacking

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
adapter stacking
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#10
09-08-2026, 10:53 PM
Maybe, but I had the opposite result. I get why that seems right, but on M3 Max the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.
measure twice, benchmark three times
Find
Reply


Messages In This Thread
adapter stacking - by benchplease - 09-02-2026, 09:00 AM
Re: adapter stacking - by localtinker - 09-03-2026, 09:31 PM
Re: adapter stacking - by circuitworks90 - 09-04-2026, 05:52 AM
Re: adapter stacking - by cacheline - 09-08-2026, 10:53 PM
Re: adapter stacking - by nanobrook - 09-04-2026, 08:23 AM
Re: adapter stacking - by kernelarch - 09-04-2026, 09:07 PM
Re: adapter stacking - by benchplease - 09-08-2026, 10:21 PM
Re: adapter stacking - by northgrid33 - 09-04-2026, 09:53 PM
Re: adapter stacking - by cudapeak - 09-05-2026, 10:20 PM
Re: adapter stacking - by rocmriley - 09-08-2026, 10:41 PM
Re: adapter stacking - by benchplease - 09-09-2026, 12:07 AM
Re: adapter stacking - by quiethouse - 09-10-2026, 12:13 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)