Inference › Drivers / Frameworks / Toolkits › NVIDIA / CUDA v
NVIDIA driver regression

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Threaded Mode
NVIDIA driver regression
flintriver50 Offline
Member
***
Posts: 51
Threads: 8
Joined: Sep 2026
Reputation: 0
#1
10-08-2026, 02:42 PM
Has anyone else run into this?

My current setup is vLLM with 7900 XTX, and I keep running into token cost.

If you've tested something similar, what did you keep and what did you stop bothering with?
learning in public
Find
Reply
marbleyard32 Offline
Junior Member
**
Posts: 30
Threads: 3
Joined: Sep 2026
Reputation: 0
#2
10-10-2026, 02:52 AM
Quote:Has anyone else run into this?

I don't think that's the whole story. I've seen people blame tool calling when the real issue was much more mundane. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Find
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)