clm_ec7951a036c342fc87a3cac23d57716e_r1

IX2-0448

① SA Source

• Source: 開啟完整 SA 文章
• Section: Disaggregated Prefill
• Line hint: 664

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

Incoming prefill requests stall in-flight decode batches, increasing both time-to-first-token and inter-token latency

Context After

Source: DistServe ↗

② Atomic Claim

新的 prefill requests 會阻塞進行中的 decode batches，同時拉高 time-to-first-token 與 inter-token latency。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "LATENCY",
  "context_nodes": [
    {
      "id": "04_knowledge_base/Decode",
      "label": "decode"
    }
  ],
  "entity": {
    "id": "04_knowledge_base/Prefill",
    "label": "prefill"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "新的 prefill requests 會阻塞進行中的 decode batches，同時拉高 time-to-first-token 與 inter-token latency。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	prefill	Prefill
context_0	decode	Decode

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。