IX2-0475
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
any given GPU has roughly a low double digit percent chance of receiving zero routed tokens in a given layer
Context After
Source: SemiAnalysis
② Atomic Claim
在這種情況下，任一 GPU 在某一層完全收不到 routed tokens 的機率約為低雙位數百分比。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "UNSPECIFIED_ATTRIBUTE",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/GPU",
"label": "GPU"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "在這種情況下，任一 GPU 在某一層完全收不到 routed tokens 的機率約為低雙位數百分比。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | GPU | GPU |
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。