IX2-0065
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Interactivity vs Throughput Tradeoff - Line hint:
97
Context Before
Source: SemiAnalysis
Evidence
For instance, real-time speech models require extremely low latency so that the end user can maintain a natural “conversation” with the LLM
Context After
The Cost/Perf per TCO vs Interactivity/End-to-End Latency curve mostly follows the Throughput vs Interactivity/End-to-End Latency Curve: More tokens/hour leads to a lower cost per token as fixed $/hour costs are amortized over more tokens produced.
Prefill and Decode Phases
② Atomic Claim
例如 real-time speech model 需要極低延遲，才能讓終端使用者與 LLM 維持自然的「對話」。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "LATENCY",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/Large language model",
"label": "LLM"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "例如 real-time speech model 需要極低延遲，才能讓終端使用者與 LLM 維持自然的「對話」。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | LLM | 04_knowledge_base/Large language model |
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。