IX2-0525
① SA Source
- Source: 開啟完整 SA 文章
- Section:
GPT-OSS 120B Single Node - Line hint:
754
Context Before
Source: SemiAnalysis InferenceX ↗
Evidence
The output token throughput per GPU more than doubles in the ~100 tok/s/user interactivity range, showing the impact of the NVL72’s larger scale up domain
Context After
Source: SemiAnalysis InferenceX ↗
② Atomic Claim
在約 100 tok/s/user 的 interactivity 區間，NVL72 較大的 scale-up domain 使每顆 GPU 的 output token throughput 提升超過 2 倍。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"comparison_expression": "在約 100 tok/s/user 的 interactivity 區間，NVL72 較大的 scale-up domain 使每顆 GPU 的 output token throughput 提升超過 2 倍。",
"entities": [
{
"id": "04_knowledge_base/GPU",
"label": "GPU"
}
],
"frame_type": "COMPARISON",
"metric": "THROUGHPUT",
"operator": "MULTIPLE_OF",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"100 tok/s/user",
"2"
],
"temporal_mentions": []
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| comparison_entity_0 | GPU | GPU |
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。