IX2-0447

① SA Source

Context Before

Disaggregated Prefill

Disaggregated prefill, sometimes referred to as prefill-decode (PD) disaggregation, is the process of performing prefill and decode phases of LLM inference on separate nodes. Prefill occurs when a request is first processed, and a forward pass is computed on all tokens at once, thereby “prefilling” the KV cache for this request. This is a compute-intensive operation as all tokens feed through the forward pass in parallel. Tokens are then generated or “decoded” one at a time, loading the KV cache from HBM at each decode step. This is a memory-intensive process as the growing KV cache is constantly being loaded.

Evidence

In traditional single-node inference, engines interleave prefill and decode on the same GPUs

Context After

image

Source: DistServe

② Atomic Claim

傳統 single-node inference engine 會讓 prefilldecode 交錯執行在同一批 GPUs 上。

  • Epistemic Mode: ASSERTED
  • Mapping Status: PARTIAL

③ Semantic Frame

{
  "attribute": "UNSPECIFIED_ATTRIBUTE",
  "context_nodes": [
    {
      "id": "04_knowledge_base/Decode",
      "label": "decode"
    },
    {
      "id": "04_knowledge_base/GPU",
      "label": "GPUs"
    }
  ],
  "entity": {
    "id": "04_knowledge_base/Prefill",
    "label": "prefill"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "傳統 single-node inference engine 會讓 prefill 與 decode 交錯執行在同一批 GPUs 上。"
  }
}

④ Canonical Entity Mapping

RoleSurface LabelCanonical Target
entityprefillPrefill
context_0decodeDecode
context_1GPUsGPU

⑤ Human Review

請在 Properties 逐項確認:

  • 原文 → Atomic Claim 是否忠實
  • Atomic Claim → Semantic Frame 是否忠實
  • Canonical Entity mapping 是否正確
  • Epistemic mode 是否保留原文語氣
  • 最後選擇 review_action

Review state

Markdown 內文不是正式 approval。只有 Apply bridge 寫入的 Decision Ledger event 才是正式決策。