Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
benchmarks that map to real use with vLLM
#16
Maybe, but I had the opposite result. I get why that seems right, but on 4090 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.
small models can still be good
Reply


Messages In This Thread
Re: benchmarks that map to real use with vLLM - by sanevault - 09-10-2026, 09:51 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)