Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Search / Retrieval / Reranking discussion
#11
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM.
small models can still be good
Reply
#12
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Reply
#13
What worked for me was pretty simple. On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Reply
#14
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. I keep promising myself this is the last rebuild.
still benchmarking everything
Reply
#15
A couple things I'd check first. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
trying not to rebuild again
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)