clm_6da3304d3d0b46db8d0be35b2225c995_r1

IX2-0202

① SA Source

• Source: 開啟完整 SA 文章
• Section: Nvidia Disagg Prefill and WideEP
• Line hint: 360

Context Before

Source: SemiAnalysis InferenceX ↗

Nvidia Disagg Prefill and WideEP

Evidence

EP requires all-to-all communication, where every GPU needs to send tokens to every other GPU

Context After

NVLink domain (within the NVL72 rack): 72 GPUs connected via NVLink with 900 GB/s uni-directional bandwidth per GPU. This is roughly 7-10x the bandwidth of the InfiniBand/Ethernet based scale-out network.

② Atomic Claim

EP 需要 all-to-all communication，也就是每顆 GPU 都必須把 token 傳送給其他每一顆 GPU。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "COUNT",
  "context_nodes": [],
  "entity": {
    "id": "04_knowledge_base/GPU",
    "label": "GPU"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "EP 需要 all-to-all communication，也就是每顆 GPU 都必須把 token 傳送給其他每一顆 GPU。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	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。