Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Blackwell deployment chatter
#11
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Reply
#12
Quote:Can you fill in a bit more context? What model, what runtime, and roughly what context size?

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Mostly CUDA, sometimes wrong, usually measured
Reply
#13
that fixed it for me too.
Reply
#14
I tested this tonight. 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.
Reply
#15
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

If you post your exact settings, people here can probably narrow it down pretty fast.
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)