Inference › Inference Engines › vLLM / SGLang v
prefill/decode separation in practice on B200

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
prefill/decode separation in practice on B200
amberrunner Offline
Member
***
Posts: 62
Threads: 5
Joined: Sep 2026
Reputation: 0
#5
10-18-2026, 02:28 PM
Interesting, I hadn't tried that. That matches what I saw on Threadripper box. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
trying not to rebuild again
Find
Reply


Messages In This Thread
Re: prefill/decode separation in practice on B200 - by amberrunner - 10-18-2026, 02:28 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)