IX2-0195
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Unpacking Inference Providers’ Unit Economics - Line hint:
350
Context Before
Source: SemiAnalysis InferenceX
Evidence
At this high of interactivity, it becomes necessary to employ speculative decoding techniques like MTP to achieve high enough throughput to make inference economical
Context After
Lastly, we show one more chart of an FP8 DeepSeek workload served at 125 tok/s/user. This is another low latency workload where MTP considerably improves economic viability. As with the previous example, we note that at these higher ranges of interactivity, the cheapest configs all use MTP.
② Atomic Claim
在這麼高的 interactivity 下，必須採用 MTP 等 speculative decoding 技術，才能讓 throughput 高到足以使推論具經濟效益。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "THROUGHPUT",
"context_nodes": [
{
"id": "04_knowledge_base/Speculative Decoding",
"label": "speculative decoding"
}
],
"entity": {
"id": "04_knowledge_base/Multi-Token Prediction",
"label": "MTP"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "在這麼高的 interactivity 下，必須採用 MTP 等 speculative decoding 技術，才能讓 throughput 高到足以使推論具經濟效益。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | MTP | 04_knowledge_base/Multi-Token Prediction |
| context_0 | speculative decoding | 04_knowledge_base/Speculative Decoding |
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。