clm_c54de503b8fd4628a75d5a213e1c1130_r1

NIEK2-0118

① SA Source

• Source: 開啟完整 SA 文章
• Section: GPU and LPU Integration: Attention FFN Disaggregation (AFD)
• Line hint: 113

Context Before

Source: SemiAnalysis, MegaScale-Infer

Evidence

With AFD, token routing from GPUs to LPUs can become the bottleneck, especially under strict latency constraints

Context After

Source: SemiAnalysis

② Atomic Claim

在 AFD 中，從 GPUs 將 token 路由到 LPU 可能成為瓶頸，尤其是在嚴格的延遲限制下。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "LATENCY",
  "context_nodes": [
    {
      "id": "04_knowledge_base/GPU",
      "label": "GPUs"
    }
  ],
  "entity": {
    "id": "04_knowledge_base/Attention-FFN Disaggregation (AFD)",
    "label": "AFD"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "在 AFD 中，從 GPUs 將 token 路由到 LPU 可能成為瓶頸，尤其是在嚴格的延遲限制下。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	AFD	04_knowledge_base/Attention-FFN Disaggregation (AFD)
context_0	GPUs	GPU

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。