Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefill/decode separation in practice on B200
#1
Thought I'd post a small recipe because a lot of threads ask similar things.

This isn't revolutionary, but the combination of PyTorch and M3 Max felt surprisingly usable once I tuned around KV cache pressure.

If someone wants the exact settings I can clean them up and post them.
measure twice, benchmark three times
Reply


Messages In This Thread
prefill/decode separation in practice on B200 - by cacheline - 10-15-2026, 12:34 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)