+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: vLLM / SGLang (https://www.datasculpting.ai/inference/forumdisplay.php?fid=36)
+--- Thread: prefill/decode separation in practice with Ollama (/showthread.php?tid=250)
Pages:
1
2
Re: prefill/decode separation in practice with Ollama - promptpoint - 09-19-2026
I'd approach it in a boring order. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: prefill/decode separation in practice with Ollama - turboarch95 - 09-20-2026
Quote:I'd approach it in a boring order. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not g
Appreciate the detail. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: prefill/decode separation in practice with Ollama - batchcraft - 09-20-2026
Need a little more detail here. Are you testing this on mini PC or something else?
Re: prefill/decode separation in practice with Ollama - nanogarden - 09-20-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal.