{
  "title": "Prefill gives logits for the first output token",
  "caption": "Prefill’s last prompt position supplies the first sampled token. Decode then uses generated inputs, and output can stream during subsequent steps. The phase widths are schematic. The author made this explanatory diagram. The playback is an example. Animation time is not measured runtime.",
  "alt": "Request timeline: queueing occurs before prefill, which makes prompt K/V and first-token logits. Decode extends the sequence while sampled tokens stream.",
  "sources": [
    {
      "path": "content/blog/2026-06-08_llm-inference-full-stack-systems/post.md",
      "sha256": "09bb02fb1815396601a7302f5924ed7b6b047a559ec5350a812ea9153627a653",
      "description": "Current article explanation, equations, assumptions and retained citations."
    },
    {
      "path": "research/dynamic-mechanisms-2026-10-21/before/content/blog/2026-06-08_llm-inference-full-stack-systems/illustrations/02-latency-ledger-algorithm.svg",
      "sha256": "a18d447850fad8c5c36d8ddb5e3603e8a0a73b9fe3af45ea95ea4a2dec851a72",
      "description": "Frozen prior illustration; exact pre-migration bytes retained."
    },
    {
      "path": "content/blog/2026-06-08_llm-inference-full-stack-systems/illustrations/source-notes.json",
      "description": "Existing article illustration provenance, retained unchanged."
    }
  ],
  "limitations": [
    "The playback is an example. Playback duration is not measured runtime."
  ]
}