Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
what changed after the inference shift with MLX
#5
Quote:Ran a quick check on my box. On 4090 with PyTorch, I saw basically the same behavior. The surprise was that memory pressure showed up before throughpu

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.
still benchmarking everything
Reply


Messages In This Thread
Re: what changed after the inference shift with MLX - by rocmhouse90 - 10-18-2026, 09:08 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)