Inference › Training & Customization › Dataset Creation / Curation
reranking still worth it for small sets: setup advice

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
reranking still worth it for small sets: setup advice
quantghost Offline
Junior Member
**
Posts: 29
Threads: 4
Joined: Sep 2026
Reputation: 0
#8
10-14-2026, 03:18 PM
Quote:Appreciate the detail. I ended up in about the same place using llama.cpp.

Not sure I agree there. I get why that seems right, but on 5090 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Find
Reply


Messages In This Thread
Re: reranking still worth it for small sets: setup advice - by quantghost - 10-14-2026, 03:18 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)