NIEK2-0100
① SA Source
- Source: 開啟完整 SA 文章
- Section:
GPU and LPU Integration: Attention FFN Disaggregation (AFD) - Line hint:
87
Context Before
Source: Nvidia
Now with an understanding of what LPUs are good for we can understand how they fit into inference setups. NVIDIA introduced LPUs to improve the performance of high interactivity scenarios. In those scenarios, LPUs can leverage their low-latency capabilities to improve the decode phase latencies. One way LPUs can improve decode phase latencies is by applying the Attention FFN Disaggregation (AFD) technique, introduced in MegaScale-Infer ↗ and Step-3 ↗.
Evidence
Decode is latency-sensitive because the model predicts new tokens one by one
Context After
Source: SemiAnalysis
② Atomic Claim
Decode 對延遲非常敏感，因為模型必須逐一預測新的 token。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "LATENCY",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/Decode",
"label": "Decode"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "Decode 對延遲非常敏感，因為模型必須逐一預測新的 token。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | Decode | Decode |
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。