Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
paged attention observations with MLX
#12
Quote:That matches what I was seeing. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at wh

That matches what I was seeing. That matches what I saw on 5090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
measure twice, benchmark three times
Reply


Messages In This Thread
Re: paged attention observations with MLX - by cacheline - 10-11-2026, 10:11 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)