clm_cbce1903fd91406bbdd58318bc63f4d1_r1

IX2-0426

① SA Source

• Source: 開啟完整 SA 文章
• Section: WideEP
• Line hint: 652

Context Before

_A WideEP EP64 DP64 deployment of DeepSeek R1. All 256 experts per layer are divided evenly among the 64 GPUs (8 nodes), and attention and other non-expert weights (shared expert, gating network, RMSNorm, LM head, etc.) are replicated across all 64 DP ranks. _Source: SemiAnalysis

Evidence

On a 64-GPU DP64/EP64 deployment, every GPU stores an identical copy of the ~40B non-expert parameters

Context After

Adding tensor parallelism within groups of GPUs addresses this. In an EP64/DP8/TP8 configuration, the 64 GPUs are organized into 8 DP groups of 8 GPUs each. Within each TP group, the attention projections, shared expert, normalization, and LM head are sharded 8 ways, so each GPU holds only 1/8th of the non-expert weights. Across the full cluster, the 256 experts are still distributed one-per-4-GPUs as before.

Pure DEP has a single communication pattern: all-to-all for expert routing. Adding TP introduces a second all-reduce within each TP group for the attention and non-expert computations. The key design principle is to place TP groups within a single node, where NVLink or MNNVL provides high-bandwidth interconnect, and run EP/DP across nodes, where the all-to-all communication pattern can tolerate higher latency.

② Atomic Claim

在 64-GPU DP64/EP64 deployment 中，每顆 GPU 都會儲存完全相同的一份約 40B non-expert parameters。

• Epistemic Mode: ASSERTED
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "comparison_expression": "在 64-GPU DP64/EP64 deployment 中，每顆 GPU 都會儲存完全相同的一份約 40B non-expert parameters。",
  "entities": [
    {
      "id": "04_knowledge_base/GPU",
      "label": "GPU"
    }
  ],
  "frame_type": "COMPARISON",
  "metric": "COUNT",
  "operator": "EQUAL_TO",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "64",
      "40B"
    ],
    "temporal_mentions": []
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
comparison_entity_0	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。