Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefill/decode separation in practice on B200
#6
My first guess would be this: If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
throughput matters, but tail latency matters too
Reply


Messages In This Thread
Re: prefill/decode separation in practice on B200 - by batchsize - 10-18-2026, 03:34 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)