Inference › Training & Customization › Distillation v
when RAG was overkill on 5090

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
when RAG was overkill on 5090
northgarden37 Offline
Junior Member
**
Posts: 39
Threads: 4
Joined: Sep 2026
Reputation: 0
#1
10-09-2026, 03:17 AM
I figured I'd ask here before changing everything.

My current setup is PyTorch with GB200, and I keep running into VRAM headroom.

Not looking for the perfect answer, mostly what worked in real use.

This is mostly for local work rather than public serving.
Find
Reply


Messages In This Thread
when RAG was overkill on 5090 - by northgarden37 - 10-09-2026, 03:17 AM
Re: when RAG was overkill on 5090 - by cozywire - 10-12-2026, 08:16 AM
Re: when RAG was overkill on 5090 - by cozysmith - 10-09-2026, 03:19 PM
Re: when RAG was overkill on 5090 - by sanescope - 10-09-2026, 03:51 PM
Re: when RAG was overkill on 5090 - by dockridge - 10-09-2026, 05:03 PM
Re: when RAG was overkill on 5090 - by vrambandit - 10-12-2026, 07:19 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)