Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
comparing models without fooling yourself with PyTorch
#6
What worked for me was pretty simple. On Threadripper box, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
throughput matters, but tail latency matters too
Reply


Messages In This Thread
Re: comparing models without fooling yourself with PyTorch - by batchsize - 10-11-2026, 09:55 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)