clm_725d795a43f04cf9be7e7bb51c22a3f4_r1

IX2-0159

① SA Source

• Source: 開啟完整 SA 文章
• Section: Nvidia versus AMD Disagg Prefill
• Line hint: 260

Context Before

Nvidia versus AMD Disagg Prefill

With today’s release of InferenceXv2, for the first time the ML community is able to see a full Pareto frontier for open-source MI355X distributed inference. We show Pareto curves for the B200 and MI355X with and without enabling MTP.

Evidence

Both the B200 and the MI355X benefit from employing MTP, and we observe the same relative performance improvement for both chips when using MTP

Context After

Source: SemiAnalysis InferenceX ↗

② Atomic Claim

B200 與 MI355X 都能受惠於 MTP，兩顆晶片使用 MTP 時的相對效能改善幅度相近。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "additional_nodes": [
    {
      "id": "04_knowledge_base/Multi-Token Prediction",
      "label": "MTP"
    }
  ],
  "frame_type": "RELATION",
  "object": {
    "id": "04_knowledge_base/MI355X",
    "label": "MI355X"
  },
  "predicate": "USES",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "subject": {
    "id": "04_knowledge_base/NVIDIA B200",
    "label": "B200"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
subject	B200	04_knowledge_base/NVIDIA B200
object	MI355X	MI355X
additional_0	MTP	04_knowledge_base/Multi-Token Prediction

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。