SA260324R-0127
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Speculative Decoding - Line hint:
161
Context Before
Speculative decoding usually boosts output token per decode step by 1.5 to 2 tokens, depending on the draft model / MTP accuracy.
Evidence
With its low latency capabilities, LPUs can further increase the latency savings and improve throughput.
Context After
For LPUs, deploying a draft model or MTP layers is quite different from applying AFD. FFNs are stateless, while draft models and MTP layers require dynamic KV cache loading. Each FFN is around hundreds of megabytes, whereas draft models and MTP layers take up tens of gigabytes. To support this memory usage, LPUs can access up to 256 GB of DDR5 per Fabric Expansion Logic FPGAs on the LPX compute tray.
② Atomic Claim
憑藉低 latency 能力，LPU 可進一步提高 latency savings 並改善 throughput。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "PERFORMANCE_EFFECT",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/Groq LPU",
"label": "LPU"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "低 latency 能力可進一步提高 latency savings 並改善 throughput。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | LPU | 04_knowledge_base/Groq LPU |
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。