Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefill/decode separation in practice with Ollama
#6
I tested this tonight. On mini PC with PyTorch, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
throughput matters, but tail latency matters too
Reply


Messages In This Thread
Re: prefill/decode separation in practice with Ollama - by batchsize - 09-16-2026, 01:22 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)