VR2R-0225_r1

VR2R-0225

① SA Source

• Source: 開啟完整 SA 文章
• Section: BlueField-4
• Line hint: 194

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.

Evidence

Host DRAM extends capacity but remains node-bound

Context After

and limited in aggregate footprint and ultimately has limited capacity.

② Atomic Claim

Host DRAM 可以延伸 capacity，但仍受限於單一 node。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "HOST_CAPACITY_EXTENSION_AND_NODE_BOUND_LIMIT",
  "context_nodes": [],
  "entity": {
    "id": "04_knowledge_base/DRAM",
    "label": "DRAM"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "extends capacity but remains node-bound."
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	DRAM	DRAM

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。