Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
why did throughput drop after update: setup advice
#1
Posting this in case it saves someone else a little time.

I'm not trying to build a perfect architecture diagram. I just want a sane starting point around MLX and Threadripper box.

I'm especially interested in mistakes worth avoiding.

This is mostly for local work rather than public serving.
Reply
#2
worth checking the driver first.
curious and caffeinated
Reply
#3
Thanks, that helps. That matches what I saw on 4090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Reply
#4
following this because I'm in the same boat.
image models by night, local pipelines by day
Reply
#5
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at long context. Not glamorous advice, but repeatable baselines save a lot of time.
routing beats arguing over one perfect model
Reply
#6
Interesting, I hadn't tried that. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Reply
#7
I hit almost the same issue last night.
Reply
#8
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Reply
#9
Interesting, I hadn't tried that. The pattern around embeddings has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Reply
#10
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
trying not to rebuild again
Reply


Forum Jump:


Users browsing this thread: 2 Guest(s)