Inference › RAG & Knowledge Systems › RAG v
where reranking mattered for FLUX

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Threaded Mode
where reranking mattered for FLUX
turbogrid11 Offline
Junior Member
**
Posts: 48
Threads: 7
Joined: Sep 2026
Reputation: 0
#11
10-17-2026, 06:58 AM
Appreciate the detail. That matches what I saw on B200.
retrieval before vibes
Find
Reply
homelabhenry Offline
Member
***
Posts: 128
Threads: 12
Joined: Sep 2026
Reputation: 0
#12
10-18-2026, 06:04 PM
Good point. 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.
rack in the garage • local models everywhere
Find
Reply
sparrowkite53 Offline
Junior Member
**
Posts: 38
Threads: 5
Joined: Sep 2026
Reputation: 0
#13
10-19-2026, 01:36 AM
Quote:Not sure I agree there. I've seen people blame tokens/sec when the real issue was much more mundane.

I hit almost the same issue last night.
Find
Reply
quietsupply11 Offline
Junior Member
**
Posts: 34
Threads: 3
Joined: Aug 2026
Reputation: 0
#14
10-19-2026, 04:33 AM
Quote:
Quote:Not sure I agree there. I've seen people blame tokens/sec when the real issue was much more mundane.

Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Find
Reply
routeforge64 Offline
Junior Member
**
Posts: 29
Threads: 2
Joined: Sep 2026
Reputation: 0
#15
10-19-2026, 05:34 AM
Not sure I agree there. I've seen people blame tokens/sec when the real issue was much more mundane.
Find
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)