SA260324R-0108_r1

SA260324R-0108

① SA Source

• Source: 開啟完整 SA 文章
• Section: GPU and LPU Integration: Attention FFN Disaggregation (AFD)
• Line hint: 119

Context Before

As state-of-the-art mixture-of-expert (MoE) models grow increasingly sparse, tokens can choose experts from a larger expert pool.

Evidence

As a result, each expert receives fewer tokens, leading to lower utilization.

Context After

This motivates attention and FFN disaggregation. If a GPU only performs attention operations, its HBM capacity can be fully allocated to KV cache, increasing the total number of tokens it can process, which then increases the tokens each expert processes on average.

② Atomic Claim

因此，每個 expert 分到的 token 變少，導致 utilization 降低。

• Epistemic Mode: ASSERTED
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "frame_type": "CLAIM_ONLY",
  "qualifiers": {
    "condition_text": "因 expert pool 擴大且模型更 sparse",
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "reason": "DEPENDENT_ON_PRIOR_MOE_CONTEXT_WITH_NO_CANONICAL_ENTITY_IN_FRAGMENT",
  "statement": "因此，每個 expert 分到的 token 變少，導致 utilization 降低。"
}

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。