IX2-0109

① SA Source

Context Before

image

Source: SemiAnalysis InferenceX

Evidence

B200 SGLang has seen steady and continuous improvement for both FP4 and FP8 scenarios since our initial launch, with throughput per GPU doubling at some interactivity levels since last October

Context After

image

Source: SemiAnalysis InferenceX

② Atomic Claim

自去年 10 月以來,在部分 interactivity 水準,B200 SGLang 的每 GPU throughput 已提高一倍。

  • Epistemic Mode: ASSERTED
  • Mapping Status: COMPLETE

③ Semantic Frame

{
  "comparison_expression": "自去年 10 月以來,在部分 interactivity 水準,B200 SGLang 的每 GPU throughput 已提高一倍。",
  "entities": [
    {
      "id": "04_knowledge_base/NVIDIA B200",
      "label": "B200"
    },
    {
      "id": "04_knowledge_base/SGLang",
      "label": "SGLang"
    },
    {
      "id": "04_knowledge_base/GPU",
      "label": "GPU"
    }
  ],
  "frame_type": "COMPARISON",
  "metric": "THROUGHPUT",
  "operator": "MULTIPLE_OF",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "10"
    ],
    "temporal_mentions": []
  }
}

④ Canonical Entity Mapping

RoleSurface LabelCanonical Target
comparison_entity_0B20004_knowledge_base/NVIDIA B200
comparison_entity_1SGLangSGLang
comparison_entity_2GPUGPU

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。