clm_a53c3e2bbd6343b893e8fe9df54a7114_r1

IX2-0040

① SA Source

• Source: 開啟完整 SA 文章
• Section: Key Observations and Results to Highlight
• Line hint: 53

Context Before

While performance is competitive on AMD when enabling just a subset of the SOTA inference optimizations, enabling all three major optimizations that labs use, AMD’s performance is currently not competitive with Nvidia’s. We strongly recommend to AMD that they focus heavily on composability of different inference optimizations. We have been told that AMD will start focusing on software composability of FP4+distributed inferencing across their whole software stack. This will happen after Chinese New Year as most of their disagg prefill+wideEP 10x inference engineers are based in China

Nvidia’s GB300 NVL72 doesn’t disappoint. It achieves up to 100x on FP8 vs FP4 compared to even a strong H100 disagg+wideEP+MTP baseline and 65x on FP8 vs FP8. On H100 vs GB200 NVL72, we see up to 55x realized performance difference at 75 tok/s/user. Rack scale Blackwell NVL72 is framemogging hopper and makes hopper looks like it is jestermaxxing. As Jensen said at GTC 2025, he is chief revenue destroyer. ↗

Evidence

At GTC 2024, Jensen claimed that Blackwell will deliver up to 30x perf on inference compared to H100

Context After

Source: SemiAnalysis InferenceX ↗

② Atomic Claim

Jensen 在 GTC 2024 宣稱，Blackwell 的推論效能最高可達 H100 的 30 倍。

• Epistemic Mode: ATTRIBUTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "comparison_expression": "Jensen 在 GTC 2024 宣稱，[[04_knowledge_base/Blackwell|Blackwell]] 的推論效能最高可達 [[04_knowledge_base/H100|H100]] 的 30 倍。",
  "entities": [
    {
      "id": "04_knowledge_base/Blackwell",
      "label": "Blackwell"
    },
    {
      "id": "04_knowledge_base/H100",
      "label": "H100"
    }
  ],
  "frame_type": "COMPARISON",
  "metric": "COMPUTE_PERFORMANCE",
  "operator": "MULTIPLE_OF",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "30x"
    ],
    "temporal_mentions": [
      "GTC 2024"
    ]
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
comparison_entity_0	Blackwell	Blackwell
comparison_entity_1	H100	H100

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。