+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Prompting & Context Engineering (https://www.datasculpting.ai/inference/forumdisplay.php?fid=15)
+--- Forum: Structured Output (https://www.datasculpting.ai/inference/forumdisplay.php?fid=63)
+--- Thread: how strict do you make schemas (/showthread.php?tid=317)
Pages:
1
2
Re: how strict do you make schemas - mangovault67 - 09-26-2026
Good point. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: how strict do you make schemas - vectorport - 09-26-2026
subscribed, curious where this lands.
Re: how strict do you make schemas - promptpoint - 09-26-2026
Quote:subscribed, curious where this lands.
What worked for me was pretty simple. If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
Re: how strict do you make schemas - tinycontext - 09-28-2026
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
Re: how strict do you make schemas - rocmstack25 - 09-28-2026
Quote:A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there.
Re: how strict do you make schemas - tinycontext - 10-01-2026
following this because I'm in the same boat.