IX2-0221
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Nvidia Disagg Prefill and WideEP - Line hint:
378
Context Before
SemiAnalysis InferenceX is free open source software and reader-supported. To receive new posts and support our work, consider becoming a free or paid subscriber.
Subscribed
Evidence
The total HBM bandwidth of all 32 chips is applied to loading a single copy of the model
Context After
Source: SemiAnalysis InferenceX ↗
② Atomic Claim
32 顆晶片的總 HBM bandwidth 可以一起用來載入單一份模型。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "BANDWIDTH",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/HBM",
"label": "HBM"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"32"
],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [
"32"
],
"value_text": "32 顆晶片的總 HBM bandwidth 可以一起用來載入單一份模型。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | HBM | HBM |
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。