SA260324R-0124

① SA Source

Context Before

For a decoding step of context N tokens, adding k additional tokens during forward pass (a warm prefill of k new tokens) marginally increases the latency when k << N.

Evidence

Using this property, speculative decoding uses a small draft model or MTP layers to predict k new tokens, saving time since small models have lower latency per decode step.

Context After

To verify the draft tokens, the main model only needs one warm prefill of k new tokens, at the latency cost of roughly a single decode step.

② Atomic Claim

利用上述特性,speculative decoding 會使用較小的 draft model 或 MTP layer 預測 k 個新 token;因小模型每個 decode step 的 latency 較低,因此可以節省時間。

  • Epistemic Mode: ASSERTED
  • Mapping Status: PARTIAL

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/Speculative Decoding",
        "label": "speculative decoding"
      },
      "role": "technique"
    },
    {
      "node": {
        "id": "04_knowledge_base/Multi-Token Prediction",
        "label": "MTP"
      },
      "role": "prediction_component"
    },
    {
      "node": {
        "id": "04_knowledge_base/Decode",
        "label": "decode"
      },
      "role": "latency_reference"
    }
  ],
  "qualifiers": {
    "condition_text": "draft model 在此 claim 沒有 canonical entity",
    "numeric_mentions": [
      "k"
    ],
    "temporal_mentions": []
  },
  "relation_type": "PREDICTS_DRAFT_TOKENS_TO_REDUCE_LATENCY"
}

④ Canonical Entity Mapping

RoleSurface LabelCanonical Target
techniquespeculative decoding04_knowledge_base/Speculative Decoding
prediction_componentMTP04_knowledge_base/Multi-Token Prediction
latency_referencedecodeDecode

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。