Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefill bottlenecks on longer prompts with vLLM
#1
This keeps coming up in conversation so I figured I'd start a thread.

One thing I keep noticing is that people underestimate continuous batching until they actually try to run this stuff for more than one afternoon.

Curious whether that lines up with what other people are seeing.
trying not to rebuild again
Reply


Messages In This Thread
prefill bottlenecks on longer prompts with vLLM - by cudaline - 08-23-2026, 01:48 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)