clm_7bdff2715dfb42409e8402b1c0f18010_r1

IX2-0422

① SA Source

• Source: 開啟完整 SA 文章
• Section: WideEP
• Line hint: 650

Context Before

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.

Evidence

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.)

Context After

The above configurations use only DP+EP (also known as DEP), where each GPU holds a full replica of all non-expert weights. As GPU count grows, this replication becomes increasingly wasteful. On a 64-GPU DP64/EP64 deployment, every GPU stores an identical copy of the ~40B non-expert parameters.

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.

② Atomic Claim

每層 256 個 experts 平均分到 64 顆 GPUs（8 nodes），attention 與其他 non-expert weights（shared expert、gating network、RMSNorm、LM head 等）則採複製方式。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "COUNT",
  "context_nodes": [],
  "entity": {
    "id": "04_knowledge_base/GPU",
    "label": "GPUs"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "256",
      "64",
      "8"
    ],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [
      "256",
      "64",
      "8"
    ],
    "value_text": "每層 256 個 experts 平均分到 64 顆 GPUs（8 nodes），attention 與其他 non-expert weights（shared expert、gating network、RMSNorm、LM head 等）則採複製方式。"
  }
}

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。