clm_07766083e6ab4b45a86abdc4310b6355_r3

SA260324R-0100

回到這篇 SA Coverage

① SA Source

• Source: 開啟完整 SA 文章
• Section: GPU and LPU Integration: Attention FFN Disaggregation (AFD)
• Line hint: 87

Context Before

Source: Nvidia

Now with an understanding of what LPUs are good for we can understand how they fit into inference setups. NVIDIA introduced LPUs to improve the performance of high interactivity scenarios. In those scenarios, LPUs can leverage their low-latency capabilities to improve the decode phase latencies. One way LPUs can improve decode phase latencies is by applying the Attention FFN Disaggregation (AFD) technique, introduced in MegaScale-Infer ↗ and Step-3 ↗.

Evidence

As we explained in our InferenceX article ↗, LLM inference involves two phases: prefill and decode. Prefill processes the full input context: It is compute-intensive, which is suitable for GPUs. On the other hand, decode predicts new tokens and is memory-bounded. Decode is latency-sensitive because the model predicts new tokens one by one, and LPU’s high SRAM bandwidth and low-latency capabilities can help accelerate this iterative process.

Context After

Source: SemiAnalysis

② Atomic Claim

Groq LPU high SRAM bandwidth and low latency can accelerate the iterative token-by-token decode process.

• Epistemic Mode: ASSERTED
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "attribute": "PERFORMANCE_CHARACTERISTICS",
  "context_nodes": [
    {
      "id": "04_knowledge_base/SRAM",
      "label": "SRAM"
    }
  ],
  "entity": {
    "id": "04_knowledge_base/Groq LPU",
    "label": "LPU"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": "this iterative process 的指涉依賴前文",
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "Groq LPU high SRAM bandwidth and low latency can accelerate the iterative token-by-token decode process."
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	LPU	04_knowledge_base/Groq LPU
context_0	SRAM	SRAM

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

Groq LPU high SRAM bandwidth and low latency can accelerate the iterative token-by-token decode process.

V2 Semantic Frame Draft

{
  "attribute": "PERFORMANCE_CHARACTERISTICS",
  "context_nodes": [
    {
      "id": "04_knowledge_base/SRAM",
      "label": "SRAM"
    }
  ],
  "entity": {
    "id": "04_knowledge_base/Groq LPU",
    "label": "LPU"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": "this iterative process 的指涉依賴前文",
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "Groq LPU high SRAM bandwidth and low latency can accelerate the iterative token-by-token decode process."
  }
}

V2 Revision Metadata Draft

{
  "epistemic_mode": "ASSERTED",
  "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。