VR2R-0227_r1

VR2R-0227

① SA Source

• Source: 開啟完整 SA 文章
• Section: BlueField-4
• Line hint: 196

Context Before

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.

Evidence

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.

Context After

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.

② Atomic Claim

另一方面，traditional shared storage 的設計重點是 durability 而不是 latency，因此 access time 與 power overhead 較高，不適合參與 decode loop。

• Epistemic Mode: ASSERTED
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "attribute": "TRADITIONAL_SHARED_STORAGE_SUITABILITY",
  "context_nodes": [],
  "entity": {
    "id": "04_knowledge_base/Decode",
    "label": "decode"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": "shared storage is plain text in source claim",
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "traditional shared storage is unsuitable for the decode loop because of higher access time and power overhead."
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	decode	Decode

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。