Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefill bottlenecks on longer prompts
#11
Appreciate the detail. I don't think your conclusion is far off.
Reply
#12
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
small models can still be useful
Reply
#13
I'd approach it in a boring order. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
image models by night, local pipelines by day
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)