IX2-0481
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Optimizing Inference with Wide EP + Disaggregated Serving - Line hint:
690
Context Before
Source: SemiAnalysis
Evidence
Configurations in this range use TEP: tensor parallelism for attention (all GPUs collaborate on each attention computation), expert parallelism for MoE layers (experts assigned to specific GPUs with all-to-all routing)
Context After
Source: SemiAnalysis InferenceX ↗
② Atomic Claim
此區間 configurations 使用 TEP：attention 採 tensor parallelism，由所有 GPUs 協同完成每次 attention；MoE layers 則採 expert parallelism，把 experts 分配到特定 GPUs 並透過 all-to-all routing。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "04_knowledge_base/Tensor Parallelism",
"label": "tensor parallelism"
},
"role": "user_or_subject"
},
{
"node": {
"id": "04_knowledge_base/GPU",
"label": "GPUs"
},
"role": "used_entity"
},
{
"node": {
"id": "04_knowledge_base/Mixture of Experts",
"label": "MoE"
},
"role": "used_entity"
},
{
"node": {
"id": "04_knowledge_base/Expert Parallelism",
"label": "expert parallelism"
},
"role": "used_entity"
}
],
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"relation_type": "USES"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| user_or_subject | tensor parallelism | 04_knowledge_base/Tensor Parallelism |
| used_entity | GPUs | GPU |
| used_entity | MoE | 04_knowledge_base/Mixture of Experts |
| used_entity | expert parallelism | 04_knowledge_base/Expert Parallelism |
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。