Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
PyTorch compile got faster?
#1
Spent some time on this today and wanted to compare notes.

I've gone back and forth between SGLang and llama.cpp for Llama. The interesting difference for me has been speculative decoding.

What would you pick if you had to live with it for a few months?
Reply


Messages In This Thread
PyTorch compile got faster? - by dockridge - 10-18-2026, 05:05 PM
Re: PyTorch compile got faster? - by deepseeked - 10-19-2026, 03:31 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)