clm_4e06808fb7394372a494283ea2e15f97_r1

IX2-0486

① SA Source

• Source: 開啟完整 SA 文章
• Section: Optimizing Inference with Wide EP + Disaggregated Serving
• Line hint: 696

Context Before

Source: SemiAnalysis InferenceX ↗

Evidence

run with separate parallelism strategies

Context After

On the low interactivity end of the frontier, there are fewer concurrent requests in flight, so a single prefill instance can keep pace with incoming demand. Yet each request still requires 1024 decode steps, and at high interactivity those steps must be fast. Recipes in this region shift to more decode nodes than prefill (1P3D, 1P4D), with each decode instance running TEP at low batch size. Tensor parallelism on attention minimizes per-step latency by sharding the computation across all GPUs in the instance, while expert parallelism handles MoE routing at the moderate batch sizes where EP load balance is sufficient. Multiple small-batch decode instances, rather than fewer large-batch ones, keep per-token latency low while still providing enough concurrent serving capacity.

② Atomic Claim

Prefill 與 decode 可以分別使用不同 parallelism strategies。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "additional_nodes": [],
  "frame_type": "RELATION",
  "object": {
    "id": "04_knowledge_base/Decode",
    "label": "decode"
  },
  "predicate": "USES",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "subject": {
    "id": "04_knowledge_base/Prefill",
    "label": "Prefill"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
subject	Prefill	Prefill
object	decode	Decode

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。