Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Blackwell deployment chatter: early impressions
#1
Did a bit of testing and thought I'd post the result here.

I tried this with Gemma using PyTorch on Threadripper box. The headline result was better than I expected, but router policy still ended up being the limiting factor.

Happy to post more details if anyone wants them.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Mostly CUDA, sometimes wrong, usually measured
Reply


Messages In This Thread
Blackwell deployment chatter: early impressions - by kernelmike - 10-10-2026, 03:52 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)