Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Help with Search / Retrieval / Reranking
#11
Quote:
Quote:I'd start with the simpler stack.

Can you fill in a bit more context? Are you testing this on A6000 or something else?
Reply
#12
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Reply
#13
Good point. I ended up in about the same place using LM Studio. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
learning in public
Reply
#14
Need a little more detail here. Are you testing this on GB200 or something else?
Reply
#15
Good point. I don't think your conclusion is far off.
trying not to rebuild again
Reply
#16
same here on my side.
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)