clm_82fbedceaa8a45dc8f11bc4be91187d4_r1

IX2-0114

① SA Source

• Source: 開啟完整 SA 文章
• Section: DeepSeek R1
• Line hint: 163

Context Before

Source: SemiAnalysis InferenceX ↗

Evidence

The use of MoRI has also delivered good speedups in the span of more than a month, with throughput per GPU increasing by more than 20% in the 20-45 tok/s/user interactivity range

Context After

Source: SemiAnalysis InferenceX ↗

② Atomic Claim

在超過一個月的期間內，MoRI 也帶來明顯加速；在 20～45 tok/s/user interactivity 區間，每 GPU throughput 提升超過 20%。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "THROUGHPUT",
  "context_nodes": [
    {
      "id": "04_knowledge_base/GPU",
      "label": "GPU"
    }
  ],
  "entity": {
    "id": "04_knowledge_base/AMD MoRI backend",
    "label": "MoRI"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "20",
      "45 tok/s/user",
      "20%"
    ],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [
      "20",
      "45 tok/s/user",
      "20%"
    ],
    "value_text": "在超過一個月的期間內，MoRI 也帶來明顯加速；在 20～45 tok/s/user interactivity 區間，每 GPU throughput 提升超過 20%。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	MoRI	04_knowledge_base/AMD MoRI backend
context_0	GPU	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。