IX2-0473
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Optimizing Inference with Wide EP + Disaggregated Serving - Line hint:
684
Context Before
Wide EP and disaggregated prefill are separate techniques that are often used together to achieve Pareto optimal performance. In this section, we walk through real results from InferenceX to build intuition for which combinations of parallelism strategy, wide EP, and disaggregated prefill are appropriate at different interactivity levels.
It helps to first understand what parallelism strategies fall on what parts of the Pareto frontier for single-node configurations. Take the example of DeepSeek R1 FP4 8k/1k on a single 8-GPU B200 node with TRT-LLM. The optimal strategy shifts as you move along the frontier, driven primarily by batch size and its effect on expert activation density.
Evidence
At low batch sizes, only a small fraction of experts activate per step
Context After
Source: SemiAnalysis
② Atomic Claim
在低 batch size 下，每個 step 只會啟動少部分 experts。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "COUNT",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/Batch size",
"label": "batch size"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "在低 batch size 下，每個 step 只會啟動少部分 experts。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | batch size | 04_knowledge_base/Batch size |
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。