NIEK2-0094
① SA Source
- Source: 開啟完整 SA 文章
- Section:
GPU and LPU Integration: Attention FFN Disaggregation (AFD) - Line hint:
85
Context Before
Source: Nvidia
Evidence
NVIDIA introduced LPUs to improve the performance of high interactivity scenarios
Context After
As we explained in our InferenceX article ↗, LLM inference involves two phases: prefill and decode. Prefill processes the full input context: It is compute-intensive, which is suitable for GPUs. On the other hand, decode predicts new tokens and is memory-bounded. Decode is latency-sensitive because the model predicts new tokens one by one, and LPU’s high SRAM bandwidth and low-latency capabilities can help accelerate this iterative process.
② Atomic Claim
NVIDIA 導入 LPU，目的是提升高互動性情境下的效能。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "UNSPECIFIED_ATTRIBUTE",
"context_nodes": [],
"entity": {
"id": "02_companies/NVDA",
"label": "NVIDIA"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "NVIDIA 導入 LPU，目的是提升高互動性情境下的效能。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | NVIDIA | NVDA |
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。