SA260324R-0102
① SA Source
- Source: 開啟完整 SA 文章
- Section:
GPU and LPU Integration: Attention FFN Disaggregation (AFD) - Line hint:
111
Context Before
Attention and FFN are subsets of operations in a model.
Evidence
In a model forward pass, attention’s output feeds into a token router
Context After
, and the token router assigns each token to k experts, where each expert is an FFN. Attention and FFN have very different performance properties. During decode phase, the GPU utilization of attention barely improves when scaling batch size due to being bounded by loading KV cache. In contrast, the GPU utilization of FFN scales with batch size comparatively better.
② Atomic Claim
關於 AFD：在模型 forward pass 中，attention 的輸出會送入 token router。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "UNSPECIFIED_ATTRIBUTE",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/Attention-FFN Disaggregation (AFD)",
"label": "AFD"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "關於 AFD：在模型 forward pass 中，attention 的輸出會送入 token router。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | AFD | 04_knowledge_base/Attention-FFN Disaggregation (AFD) |
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。