+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Fine-Tuning / LoRA (https://www.datasculpting.ai/inference/forumdisplay.php?fid=54)
+--- Thread: how much orchestration is too much (/showthread.php?tid=463)
Pages:
1
2
Re: how much orchestration is too much - oxidegrove40 - 09-29-2026
That matches what I was seeing. The pattern around prefill/decode split has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: how much orchestration is too much - southden - 09-30-2026
Appreciate the detail. I ended up in about the same place using LM Studio. The biggest change for me was simplifying the stack instead of adding one more optimization layer.