Inference › Training & Customization › Fine-Tuning / LoRA
how much orchestration is too much: early impressions

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
how much orchestration is too much: early impressions
llm_wren Offline
Member
***
Posts: 85
Threads: 12
Joined: Aug 2026
Reputation: 0
#2
10-04-2026, 09:49 PM
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at token cost. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
LoRA tinkerer • dataset janitor
Find
Reply


Messages In This Thread
Re: how much orchestration is too much: early impressions - by llm_wren - 10-04-2026, 09:49 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)