clm_c94e4cd880464cabb6d3822fc4d2fef2_r1

IX2-0410

① SA Source

• Source: 開啟完整 SA 文章
• Section: WideEP
• Line hint: 642

Context Before

_An EP8 DP8 deployment of DeepSeek R1. All 256 experts per layer are divided evenly among the 8 GPUs, whereas attention along with other non-expert weights (shared expert, gating network, RMSNorm, LM head, etc.) are replicated across all 8 DP ranks. _Source: SemiAnalysis

Evidence

This scales throughput linearly, but each GPU still holds 32 experts per layer, and each token activates at most 8 of those 32 local experts

Context After

Wide expert parallelism (WideEP) takes a different approach by scaling EP _across _nodes rather than replicating independent instances. On a 64-GPU cluster (8 nodes), DP64/EP64 places only 256/64 = 4 experts per layer per GPU, each still holding a full replica of the non-expert weights. During the MoE phase, tokens from all 64 DP ranks are dispatched via all-to-all to the GPUs hosting their routed experts.

This yields three compounding benefits over the single-node EP8 baseline. First, reducing expert footprint from 32 to 4 experts/GPU frees substantial HBM for KV cache, directly increasing per-GPU batch size capacity. Second, 64 DP ranks funneling tokens through fewer experts per GPU increases tokens-per-expert, raising arithmetic intensity (more FLOPs per byte of weights loaded) and improving compute utilization. The same expert weights service 8x more tokens per step. Third, aggregate HBM bandwidth scales linearly with GPU count; 64 GPUs loading expert weights simultaneously provide 8x the memory bandwidth of a single node, reducing memory bottleneck.

② Atomic Claim

這可讓 throughput 線性擴展，但每顆 GPU 仍需持有每層 32 個 experts，而每個 token 最多只會啟動其中 8 個 local experts。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "THROUGHPUT",
  "context_nodes": [],
  "entity": {
    "id": "04_knowledge_base/GPU",
    "label": "GPU"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "32",
      "8"
    ],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [
      "32",
      "8"
    ],
    "value_text": "這可讓 throughput 線性擴展，但每顆 GPU 仍需持有每層 32 個 experts，而每個 token 最多只會啟動其中 8 個 local experts。"
  }
}

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。