VR2R-0238
① SA Source
- Source: 開啟完整 SA 文章
- Section:
BlueField-4 - Line hint:
329
Context Before
As we noted in mid-January in our Memory Model note ↗, Nvidia’s ICMS inserts a new G3.5 tier between local SSD (G3) and shared storage (G4), optimized specifically for ephemeral, recomputable KV cache. The ICMS requires a dedicated networking layer designed exclusively for KV traffic. Wherever networking is used in this architecture, it is provisioned as a context memory network — isolated from general data movement and optimized for predictable decode latency.
The challenge with this is that the volumes of SSDs going to ICMS / CMX are quite overblown by the industry. We worked through the math in the Memory model ↗ and Tokenomics model ↗.
Evidence
BlueField-4 will be the silicon anchor of this third network. Positioned on the storage array, it terminates NVMe-oF and RDMA traffic at line rate and manages KV movement independently of host CPUs and GPUs. With 2×400G SerDes links providing 800Gb/s of bandwidth, integrated Grace CPU, and LPDDR, BlueField-4 would act as the controller for a distributed context memory fabric. In a preferred DGX-style configuration, a single BlueField-4 per tray may serve four Rubin processors, with the DPU dedicated purely to KV cache traffic and not shared with generic storage I/O.
Context After
The new CMX/ICMS ecosystem will likely include leading storage providers such as Weka, DDN, Dell Technologies, NetApp, VAST Data, and others.
Power Delivery
② Atomic Claim
在原文偏好的 DGX-style context-memory 配置中，BlueField-4 DPU 將專用於 KV cache traffic，不與 generic storage I/O 共用。
- Epistemic Mode:
HYPOTHETICAL - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "DEDICATED_TRAFFIC_ROLE",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/DPU",
"label": "DPU"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": "DPU refers to BlueField-4 from preceding claim; Preferred DGX-style context-memory configuration; one BF-4 may serve four Rubin processors",
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "dedicated purely to KV cache traffic and not shared with generic storage I/O."
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | DPU | DPU |
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
在原文偏好的 DGX-style context-memory 配置中，BlueField-4 DPU 將專用於 KV cache traffic，不與 generic storage I/O 共用。
V2 Semantic Frame Draft
{
"attribute": "DEDICATED_TRAFFIC_ROLE",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/DPU",
"label": "DPU"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": "DPU refers to BlueField-4 from preceding claim; Preferred DGX-style context-memory configuration; one BF-4 may serve four Rubin processors",
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "dedicated purely to KV cache traffic and not shared with generic storage I/O."
}
}V2 Revision Metadata Draft
{
"epistemic_mode": "HYPOTHETICAL",
"mapping_status": "PARTIAL"
}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。