Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
desk setup thread
#11
Quote:I think the bottleneck is somewhere else. I've seen people blame INT4 when the real issue was much more mundane. Could be a workload difference, but I

I'd approach it in a boring order. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
trying not to rebuild again
Reply
#12
Not sure I agree there. I get why that seems right, but on B200 the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Mostly CUDA, sometimes wrong, usually measured
Reply


Forum Jump:


Users browsing this thread: