clm_57cc468ddecc4eb3bd93f61909f68082_r1

VR2-0216

① SA Source

• Source: 開啟完整 SA 文章
• Section: BlueField-4
• Line hint: 319

Context Before

Source: Nvidia VR NVL72 BoM and Power Budget Model ↗

Evidence

The module also comes with 128GByte of on board LPDDR5x, 512Gbyte of on board pluggable SSD and an integrated AST2600 BMC from Aspeed

Context After

Speaking of BlueField-4, it is important to discuss the new offering Jensen highlighted at CES earlier this year: ICMS, or Inference Context Memory Storage — a platform that we hear may be rebranded to “CMX” at GTC. ICMS, or CMX, introduces a third, entirely separate network dedicated solely to context memory. CMX is a purpose-built KV cache fabric. As long-context inference pushes context windows toward millions of tokens and agentic concurrency scales across users and services, the current memory hierarchy used to store KVcache begins to look insufficient.

KV cache grows linearly with sequence length and multiplicatively with workload parallelism, quickly expanding beyond what any single tier of memory was designed to hold. GPU HBM, while unmatched in bandwidth and latency, is not enough on its own to store KV especially for longer sequence length queries that are becoming popular between turns or tool calls. Host DRAM extends capacity but remains node-bound and limited in aggregate footprint and ultimately has limited capacity. Meanwhile, traditional shared storage—architected for durability rather than latency —has more access time and power overhead, making it unsuitable for participation in the decode loop.

② Atomic Claim

該 module 另包含 128GByte onboard LPDDR5x、512GByte onboard pluggable SSD，以及 Aspeed AST2600 integrated BMC。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/LPDDR5X",
        "label": "LPDDR5x"
      },
      "role": "system_or_subject"
    },
    {
      "node": {
        "id": "04_knowledge_base/SSD",
        "label": "SSD"
      },
      "role": "integrated_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/BMC",
        "label": "BMC"
      },
      "role": "integrated_entity"
    }
  ],
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "128GB",
      "512GB"
    ],
    "temporal_mentions": []
  },
  "relation_type": "INTEGRATES"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
system_or_subject	LPDDR5x	LPDDR5X
integrated_entity	SSD	SSD
integrated_entity	BMC	BMC

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。