+- 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: structured output failures with vLLM (/showthread.php?tid=1392)
Pages:
1
2
Re: structured output failures with vLLM - vramport - 10-19-2026
Interesting, I hadn't tried that. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: structured output failures with vLLM - quantsupply - 10-19-2026
What exact setup are you running? Are you testing this on dual 3090 or something else?