+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: llama.cpp / GGUF (https://www.datasculpting.ai/inference/forumdisplay.php?fid=35)
+--- Thread: prefix caching in llama.cpp: setup advice (/showthread.php?tid=1021)
prefix caching in llama.cpp: setup advice - latentcraft - 10-10-2026
Posting this in case it saves someone else a little time.
I'm not trying to build a perfect architecture diagram. I just want a sane starting point around llama.cpp and 4090.
Would rather learn from your scars than collect my own all at once.
Re: prefix caching in llama.cpp: setup advice - northgrid33 - 10-12-2026
Appreciate the detail. I don't think your conclusion is far off.