IX2-0108

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

B200 SGLangFP8 情境下也持續改善。

  • Epistemic Mode: ASSERTED
  • Mapping Status: PARTIAL

③ Semantic Frame

{
  "attribute": "UNSPECIFIED_ATTRIBUTE",
  "context_nodes": [
    {
      "id": "04_knowledge_base/SGLang",
      "label": "SGLang"
    },
    {
      "id": "04_knowledge_base/FP8",
      "label": "FP8"
    }
  ],
  "entity": {
    "id": "04_knowledge_base/NVIDIA B200",
    "label": "B200"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "B200 SGLang 在 FP8 情境下也持續改善。"
  }
}

④ Canonical Entity Mapping

RoleSurface LabelCanonical Target
entityB20004_knowledge_base/NVIDIA B200
context_0SGLangSGLang
context_1FP8FP8

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。