VR2R-0686::SPLIT02
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Assembly Automation and Logistics - Line hint:
921
Context Before
Source: Nvidia VR NVL72 Component BoM and Power Budget Model ↗
Evidence
At L6, board level PCBA, Wistron and Foxconn are the main supplier of Blackwell and Rubin. For L10, Blackwell had lots of different compute tray manufacturers as they buy the Bianca boards from Nvidia to sell to their clients. For Rubin, there are only three suppliers that have the capability to do automation of Rubin compute tray. For smaller ODM or OEM, they either have their compute tray made at the three automation suppliers mentioned above or they will do it in-house without automation. Although not as efficient, compute tray assembly without automation should be much easier compared to Blackwell as well given the seamless modular design. Then at L11, the various ODMs/OEMs assemble the compute tray into the rack.
Context After
VR NVL72 TCO: BoM and Power Budget Analysis
The VR NVL72 Component BoM and Power Budget Model ↗ provides a detailed analysis on the BoM and the Power Budget of the rack system.
② Atomic Claim
Blackwell L10 manufacturers buy Bianca boards from Nvidia to sell to their clients.
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "L10_PROCUREMENT",
"context_nodes": [
{
"id": "04_knowledge_base/Bianca Board",
"label": "Bianca"
},
{
"id": "02_companies/NVDA",
"label": "Nvidia"
}
],
"entity": {
"id": "04_knowledge_base/Blackwell",
"label": "Blackwell"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "Blackwell L10 manufacturers buy Bianca boards from Nvidia to sell to their clients."
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | Blackwell | Blackwell |
| context_0 | Bianca | 04_knowledge_base/Bianca Board |
| context_1 | Nvidia | NVDA |
⑤ V2 Draft（需要修正時直接編輯）
Inline repair
只編輯以下三個 Draft 區塊。完成後將
review_action設為REQUEST_REPAIR，再手動執行 Repair Preview。
執行腳本前，Draft 不會寫入 Claim Store 或 Graph。
V2 Atomic Claim Draft
Blackwell L10 manufacturers buy Bianca boards from Nvidia to sell to their clients.
V2 Semantic Frame Draft
{
"attribute": "L10_PROCUREMENT",
"context_nodes": [
{
"id": "04_knowledge_base/Bianca Board",
"label": "Bianca"
},
{
"id": "02_companies/NVDA",
"label": "Nvidia"
}
],
"entity": {
"id": "04_knowledge_base/Blackwell",
"label": "Blackwell"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "Blackwell L10 manufacturers buy Bianca boards from Nvidia to sell to their clients."
}
}V2 Revision Metadata Draft
{
"epistemic_mode": "ASSERTED",
"mapping_status": "COMPLETE"
}⑥ 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。