NIEK2-0095
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
In those scenarios, LPUs can leverage their low-latency capabilities to improve the decode phase latencies
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
在這類情境中，LPU 可利用其低延遲能力降低 decode 階段的延遲。
- 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": "在這類情境中，LPU 可利用其低延遲能力降低 decode 階段的延遲。"
}
}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。