Inference › Drivers / Frameworks / Toolkits › PyTorch / JAX / Other Frameworks v
PyTorch compile got faster? on dual 3090

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
PyTorch compile got faster? on dual 3090
vrambandit Offline
Member
***
Posts: 168
Threads: 14
Joined: Sep 2026
Reputation: 0
#3
10-19-2026, 12:44 AM
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?
2x3090 • llama.cpp • too much VRAM is still not enough
Find
Reply


Messages In This Thread
Re: PyTorch compile got faster? on dual 3090 - by vrambandit - 10-19-2026, 12:44 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)