https://www.zhumengyao.com/scidraft/tags/inference/Recent content in Inference on SciDraft | A Hugo ThemeHugoenTue, 22 Sep 2026 07:15:00 +0900https://www.zhumengyao.com/scidraft/notes/demo-note-mermaid-sequence/Tue, 22 Sep 2026 07:15:00 +0900https://www.zhumengyao.com/scidraft/notes/demo-note-mermaid-sequence/<p><strong>Demo note.</strong> This note demonstrates what the <strong>SciDraft</strong> Hugo theme can do for academic and scientific publishing — for research institutions, researchers and students. Its content is demonstration material only: readers should ignore whether the demo content is correct.</p> <p>A language model writes one token at a time. The prompt is processed once, then each new token is appended to the sequence and fed back in, so generation is a loop between the model and the sampler rather than a single call. The sequence diagram below shows the participants and the messages between them.</p>https://www.zhumengyao.com/scidraft/notes/demo-note-mermaid-state/Mon, 21 Sep 2026 10:12:00 +0900https://www.zhumengyao.com/scidraft/notes/demo-note-mermaid-state/<p><strong>Demo note.</strong> This note demonstrates what the <strong>SciDraft</strong> Hugo theme can do for academic and scientific publishing — for research institutions, researchers and students. Its content is demonstration material only: readers should ignore whether the demo content is correct.</p> <p>The same generation loop can be described without messages, as a machine with a small number of states. This view is useful when the interesting questions are about <em>transitions</em> — when decoding starts, what keeps it running, and which conditions end it. The state diagram below is the whole lifecycle of one completion.</p>