+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Context / KV Cache (https://www.datasculpting.ai/inference/forumdisplay.php?fid=41)
+--- Thread: prefix caching on repeated workflows (/showthread.php?tid=288)
prefix caching on repeated workflows - cacheline - 09-14-2026
This keeps coming up in conversation so I figured I'd start a thread.
It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with batch size.
Wondering if this is just where the whole space is heading now.
Re: prefix caching on repeated workflows - cacheline - 09-15-2026
Thanks, that helps. I ended up in about the same place using LM Studio. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: prefix caching on repeated workflows - labline - 09-15-2026
Ran a quick check on my box. On Threadripper box with Ollama, I saw basically the same behavior. I expected the model choice to matter more than it did.