clm_867ae142107645949d0146cc743e9a77_r1

IX2-0516

① SA Source

• Source: 開啟完整 SA 文章
• Section: GPT-OSS 120B Single Node
• Line hint: 740

Context Before

Source: SemiAnalysis InferenceX ↗

GPT-OSS 120B Single Node

Evidence

The next step up is MI355X, which delivers roughly more than 2x higher token throughput per GPU at a given interactivity level, relative to that first group

Context After

Above that tier sits NVIDIA’s B200 and GB200, which outperform MI355X across the frontier. While B200 and GB200 share the same Blackwell compute die, GB200 achieves a higher throughput–interactivity curve because the platform and serving stack reduce non-compute bottlenecks at scale (interconnect/topology, CPU-GPU coupling, and runtime scheduling), translating into effective scale-out and less overhead per token.

② Atomic Claim

再上一個層級是 MI355X；在相同 interactivity 水準下，其每顆 GPU 的 token throughput 約為前述第一組的 2 倍以上。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "comparison_expression": "再上一個層級是 MI355X；在相同 interactivity 水準下，其每顆 GPU 的 token throughput 約為前述第一組的 2 倍以上。",
  "entities": [
    {
      "id": "04_knowledge_base/MI355X",
      "label": "MI355X"
    },
    {
      "id": "04_knowledge_base/GPU",
      "label": "GPU"
    }
  ],
  "frame_type": "COMPARISON",
  "metric": "THROUGHPUT",
  "operator": "MULTIPLE_OF",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "2"
    ],
    "temporal_mentions": []
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
comparison_entity_0	MI355X	MI355X
comparison_entity_1	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。