Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
router in front of vLLM: early impressions
#11
Quote:Interesting, I hadn't tried that. I ended up in about the same place using Ollama. The biggest change for me was simplifying the stack instead of addi

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tool calling. Once you know the plain path works, then add the faster path back in piece by piece.
throughput matters, but tail latency matters too
Reply
#12
subscribed, curious where this lands.
mostly local
Reply
#13
Interesting, I hadn't tried that. I ended up in about the same place using Ollama. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
measure twice, benchmark three times
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)