IX2-0232
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Nvidia Disagg Prefill and WideEP - Line hint:
386
Context Before
Source: SemiAnalysis InferenceX ↗
Generally, TP is preferred at lower concurrencies due to load balancing. At small batch sizes, EP suffers from uneven token-to-expert routing, leaving some GPUs underutilized while others are overloaded. TP avoids this since each GPU holds a slice of every expert and always gets an equal share of work. At lower concurrency, the cost of this load imbalance outweighs TP’s additional communication overhead.
Evidence
In the middle of the curve, hybrid TP+EP configurations balance both concerns using small TP groups within each expert for load balancing while EP is used across the wider set of GPUs to amortize weights and reduce communication
Context After
For higher interactivity levels (low batch size), large scale-up world sizes tend not to deliver stronger performance. B300 disagg over IB has the same performance as GB300 with NVL72, since the workload is latency-bound, not bandwidth-bound. The massive NVLink bandwidth advantage of NVL72 doesn’t matter because not even the much slower IB link is saturated by the tiny batches of tokens in flight.
Prefill/decode disaggregation also plays a role. Prefill is compute-heavy and bursty; decode is memory-bandwidth-bound and steady-state. When they share the same GPUs, they interfere with each other, causing latency jitter and wasted capacity. Separating them onto dedicated GPU pools lets each run a workload matched to its characteristics, improving effective utilization. This is why disaggregated B200 configs outperform single-node B200 in the middle of the throughput-interactivity curve. PD separation combined with wider EP across more GPUs over IB amortizes weights more efficiently than cramming both phases onto a single 8-GPU node.
② Atomic Claim
在曲線中段，hybrid TP+EP configuration 會兼顧兩者：在每個 expert 內使用小型 TP group 做 load balancing，同時在更大的 GPUs 集合間使用 EP，以分攤 weights 並降低通訊成本。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "COST",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/GPU",
"label": "GPUs"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "在曲線中段，hybrid TP+EP configuration 會兼顧兩者：在每個 expert 內使用小型 TP group 做 load balancing，同時在更大的 GPUs 集合間使用 EP，以分攤 weights 並降低通訊成本。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | GPUs | 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。