SA260324R-0113_r1

SA260324R-0113

① SA Source

• Source: 開啟完整 SA 文章
• Section: GPU and LPU Integration: Attention FFN Disaggregation (AFD)
• Line hint: 125

Context Before

Comparing the two operations, we see attention is stateful due to dynamic KV cache loading patterns, whereas FFN is stateless since the computation only depends on the token inputs.

Evidence

Thus, we disaggregate the computation of attention and FFN.

Context After

We map attention computations to GPUs, which handle dynamic workloads well. For FFNs, we map them to LPUs, since LPU architecture is inherently deterministic and benefits from static compute workloads.

② Atomic Claim

因此，attention 與 FFN 的運算會被拆分。

• Epistemic Mode: INFERRED
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "frame_type": "CLAIM_ONLY",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "reason": "ATTENTION_HAS_NO_CANONICAL_ENTITY_IN_THIS_CLAIM",
  "statement": "因此，attention 與 FFN 的運算會被拆分。"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
—	—	—

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。