IX2-0381
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Wide Expert Parallelism (WideEP) and Disaggregated Prefill - Line hint:
626
Context Before
Source: SemiAnalysis InferenceX ↗
Wide Expert Parallelism (WideEP) and Disaggregated Prefill
Evidence
We will then explain the idea of Disaggregated Prefill, how it is different from WideEP
Context After
WideEP
By now, most frontier AI labs employ Mixture of Experts (MoE) model architectures as opposed to dense. In MoE architectures, only a subset of “experts” are activated for each token. For instance, DeepSeek R1 has 671B total parameters, but only 37B active parameters. Specifically, DeepSeek R1 has 256 routed experts (and 1 shared expert) with each token being routed to 8 distinct experts. This architecture lends itself naturally to expert parallelism (EP), which evenly distributes expert weights across some number of GPUs.
② Atomic Claim
接著會介紹 Disaggregated Prefill，以及它與 WideEP 的差異。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "UNSPECIFIED_ATTRIBUTE",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/Disaggregated prefill",
"label": "Disaggregated Prefill"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "接著會介紹 Disaggregated Prefill，以及它與 WideEP 的差異。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | Disaggregated Prefill | 04_knowledge_base/Disaggregated prefill |
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。