+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Performance Tuning (https://www.datasculpting.ai/inference/forumdisplay.php?fid=42)
+--- Thread: disaggregated inference thoughts with llama.cpp (/showthread.php?tid=212)
Pages:
1
2
Re: disaggregated inference thoughts with llama.cpp - sparrowkite53 - 09-16-2026
I'd start with the simpler stack.
Re: disaggregated inference thoughts with llama.cpp - rocmhouse90 - 09-16-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: disaggregated inference thoughts with llama.cpp - stackarch - 09-16-2026
Did a small comparison this afternoon. On 7900 XTX with PyTorch, I saw basically the same behavior. I expected the model choice to matter more than it did.
Re: disaggregated inference thoughts with llama.cpp - kernelrunner - 09-16-2026
Quote:Did a small comparison this afternoon. On 7900 XTX with PyTorch, I saw basically the same behavior. I expected the model choice to matter more than it
Appreciate the detail. 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.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.