Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
router in front of vLLM: early impressions
#3
Interesting, I hadn't tried that. The pattern around prefill/decode split has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
measure twice, benchmark three times
Reply


Messages In This Thread
Re: router in front of vLLM: early impressions - by cacheline - 10-17-2026, 12:14 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)