clm_15668785ee6f45b1a224fb757db52fa7_r1

IX2-0156

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

Wide EP is not used for either of these configs as all prefill/decode instances run using EP8 at the most

Context After

Source: SemiAnalysis InferenceX ↗

② Atomic Claim

這兩個 configurations 都沒有使用 wide EP，因為所有 prefill／decode instances 最多只使用 EP8。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "additional_nodes": [
    {
      "id": "04_knowledge_base/Expert Parallelism",
      "label": "wide EP"
    }
  ],
  "frame_type": "RELATION",
  "object": {
    "id": "04_knowledge_base/Decode",
    "label": "decode"
  },
  "predicate": "USES",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "subject": {
    "id": "04_knowledge_base/Prefill",
    "label": "prefill"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
subject	prefill	Prefill
object	decode	Decode
additional_0	wide EP	04_knowledge_base/Expert Parallelism

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。