clm_d4bd3c01c7534a379422268a4ad16175_r1

VR2-0237

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

Positioned on the storage array, it terminates NVMe-oF and RDMA traffic at line rate

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

BlueField-4 可在 storage array 上以 line rate terminate NVMe-oF 與 RDMA traffic。

• Epistemic Mode: ASSERTED
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "attribute": "UNSPECIFIED_ATTRIBUTE",
  "context_nodes": [
    {
      "id": "04_knowledge_base/NVMe",
      "label": "NVMe"
    },
    {
      "id": "04_knowledge_base/RDMA",
      "label": "RDMA"
    }
  ],
  "entity": {
    "id": "04_knowledge_base/BlueField-4",
    "label": "BlueField-4"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "4"
    ],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [
      "4"
    ],
    "value_text": "BlueField-4 可在 storage array 上以 line rate terminate NVMe-oF 與 RDMA traffic。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	BlueField-4	BlueField-4
context_0	NVMe	NVMe
context_1	RDMA	RDMA

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。