SA260324R-0111_r1

SA260324R-0111

① SA Source

• Source: 開啟完整 SA 文章
• Section: GPU and LPU Integration: Attention FFN Disaggregation (AFD)
• Line hint: 125

Context Before

As state-of-the-art mixture-of-expert (MoE) models grow increasingly sparse, tokens can choose experts from a larger expert pool. As a result, each expert receives fewer tokens, leading to lower utilization. This motivates attention and FFN disaggregation. If a GPU only performs attention operations, its HBM capacity can be fully allocated to KV cache, increasing the total number of tokens it can process, which then increases the tokens each expert processes on average.

Evidence

Comparing the two operations, we see attention is stateful due to dynamic KV cache loading patterns

Context After

, whereas FFN is stateless since the computation only depends on the token inputs. Thus, we disaggregate the computation of attention and FFN. We map attention computations to GPUs, which handle dynamic workloads well. For FFNs, we map them to LPUs, since LPU architecture is inherently deterministic and benefits from static compute workloads.

② Atomic Claim

比較兩種運算後，SemiAnalysis 認為 attention 因為有動態 KV cache 載入模式，因此屬於 stateful 工作負載。

• Epistemic Mode: ASSERTED
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "attribute": "UNSPECIFIED_ATTRIBUTE",
  "context_nodes": [],
  "entity": {
    "id": "04_knowledge_base/KV cache",
    "label": "KV cache"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "比較兩種運算後，SemiAnalysis 認為 attention 因為有動態 KV cache 載入模式，因此屬於 stateful 工作負載。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	KV cache	04_knowledge_base/KV cache

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。