IX2-0150
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Nvidia TensorRT LLM and NVL72 - Line hint:
250
Context Before
Source: SemiAnalysis InferenceX ↗
Evidence
At 130 tok/s/user, the GB200 NVL72 has nearly no advantage and is even more expensive on a $/Million tokens basis
Context After
Source: SemiAnalysis InferenceX ↗
② Atomic Claim
在 130 tok/s/user 時，GB200 NVL72 以每百萬 token 成本計算甚至更貴。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "THROUGHPUT",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/GB200 NVL72",
"label": "GB200 NVL72"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"130 tok/s/user"
],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [
"130 tok/s/user"
],
"value_text": "在 130 tok/s/user 時，GB200 NVL72 以每百萬 token 成本計算甚至更貴。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | GB200 NVL72 | 04_knowledge_base/GB200 NVL72 |
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。