IX2-0216
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Nvidia Disagg Prefill and WideEP - Line hint:
372
Context Before
InfiniBand/RoCEv2 Ethernet (outside of the NVL72 rack): Typically 400-800 Gbit/s per GPU uni-directional (50-100 GB/s). Note that all our testing for Nvidia was conducted on InfiniBand based clusters.
TP shards every layer’s weight matrices across GPUs. This means that every single token at every single layer requires up to two all-reduce communications (one after the column-parallel GEMM, one after the row-parallel GEMM). For EP, all-to-all is done only at MoE layers. Each GPU sends only the tokens routed to each expert. This means cheaper comms across all layers for EP vs TP.
Evidence
Context After
SemiAnalysis InferenceX is free open source software and reader-supported. To receive new posts and support our work, consider becoming a free or paid subscriber.
Subscribed
② Atomic Claim
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "COUNT",
"context_nodes": [
{
"id": "04_knowledge_base/NVLink",
"label": "NVLink"
}
],
"entity": {
"id": "04_knowledge_base/GPU",
"label": "GPUs"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"72"
],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [
"72"
],
"value_text": "在 NVL72 上，可以讓 72 顆 GPUs 執行 EP，而完全不離開 NVLink domain。"
}
}④ Canonical Entity Mapping
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。