non-AI thing you built recently

[southtinker]

That matches what I was seeing. The pattern around structured output 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.

[batchsize]

A couple things I'd check first. If you're on TensorRT-LLM, 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.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.

[amberrunner]

My first guess would be this: On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[llmtrack26]

same here on my side.

[fastlab]

I hit almost the same issue last night.

[mellowsupply]

following this because I'm in the same boat.