08-27-2026, 02:31 PM
Quote:Need a little more detail here. Is this local-only or are you routing anything externally?
I'd approach it in a boring order. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Mostly CUDA, sometimes wrong, usually measured
