clm_8c28a4f859ab40d890b6a203042f1d05_r2

SA260324R-0117

回到這篇 SA Coverage

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. The token routing flow involves two operations: dispatch and combine. In the dispatch step, we route each token to their top k experts with an All-to-All collective operation. After experts complete their computation, we perform the combine step, where the outputs are sent back to the source location with a reverse All-to-All collective, continuing the next layer’s computation.

Context After

Source: SemiAnalysis

② Atomic Claim

token routing 流程包含兩個 operation：dispatch 與 combine。

• Epistemic Mode: ASSERTED
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "frame_type": "CLAIM_ONLY",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "2"
    ],
    "temporal_mentions": []
  },
  "reason": "TOKEN_ROUTING_DISPATCH_AND_COMBINE_HAVE_NO_CANONICAL_ENTITIES",
  "statement": "token routing 流程包含兩個 operation：dispatch 與 combine。"
}

④ Canonical Entity Mapping

• 此 CLAIM_ONLY revision 沒有 canonical Entity mapping。

⑤ V2 Draft（需要修正時直接編輯）

Inline repair

只編輯以下三個 Draft 區塊。完成後將 review_action 設為 REQUEST_REPAIR，再手動執行 Repair Preview。
執行腳本前，Draft 不會寫入 Claim Store 或 Graph。

V2 Atomic Claim Draft

token routing 流程包含兩個 operation：dispatch 與 combine。

V2 Semantic Frame Draft

{
  "frame_type": "CLAIM_ONLY",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "2"
    ],
    "temporal_mentions": []
  },
  "reason": "TOKEN_ROUTING_DISPATCH_AND_COMBINE_HAVE_NO_CANONICAL_ENTITIES",
  "statement": "token routing 流程包含兩個 operation：dispatch 與 combine。"
}

V2 Revision Metadata Draft

{
  "epistemic_mode": "ASSERTED",
  "mapping_status": "PARTIAL"
}

⑥ 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。