Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
PyTorch compile got faster? with vLLM
#7
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
still benchmarking everything
Reply


Messages In This Thread
Re: PyTorch compile got faster? with vLLM - by sparrowgrid - 09-09-2026, 08:15 PM

Forum Jump:


Users browsing this thread: 2 Guest(s)