Inference › Evaluation & Testing › Benchmarks v
benchmark result I don't trust

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
benchmark result I don't trust
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#6
10-18-2026, 10:20 PM
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
measure twice, benchmark three times
Find
Reply


Messages In This Thread
benchmark result I don't trust - by cacheline - 10-14-2026, 07:53 PM
Re: benchmark result I don't trust - by routearch - 10-15-2026, 08:31 AM
Re: benchmark result I don't trust - by routearch - 10-17-2026, 09:55 AM
Re: benchmark result I don't trust - by cacheline - 10-18-2026, 10:20 PM
Re: benchmark result I don't trust - by routearch - 10-18-2026, 10:26 PM
Re: benchmark result I don't trust - by batchpeak - 10-19-2026, 03:39 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)