SA260324R-0118
① SA Source
- Source: 開啟完整 SA 文章
- Section:
GPU and LPU Integration: Attention FFN Disaggregation (AFD) - Line hint:
131
Context Before
With AFD, token routing from GPUs to LPUs can become the bottleneck, especially under strict latency constraints. The token routing flow involves two operations: dispatch and combine.
Evidence
In the dispatch step, we route each token to their top k experts with an All-to-All collective operation.
Context After
After experts complete their computation, we perform the combine step, where the outputs are sent back to the source location with a reverse All-to-All collective, continuing the next layer’s computation.
② Atomic Claim
在 dispatch 階段，每個 token 會透過 All-to-All collective operation 被送到其 top-k experts。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"frame_type": "CLAIM_ONLY",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"k"
],
"temporal_mentions": []
},
"reason": "DISPATCH_TOKEN_EXPERTS_AND_ALL_TO_ALL_HAVE_NO_CANONICAL_ENTITIES",
"statement": "在 dispatch 階段，每個 token 會透過 All-to-All collective operation 被送到其 top-k experts。"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| — | — | — |
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。