clm_8cfd66e92f0a4ce0aaa024c92e0d3838_r1

IX2-0007

① SA Source

• Source: 開啟完整 SA 文章
• Section: Introduction
• Line hint: 23

Context Before

InferenceXv2 (formerly InferenceMAX) builds on the foundation established by InferenceMAXv1, our open-source, continuously updated inference benchmark ↗ that has set a new standard for AI inference performance and economics. InferenceMAXv1 moved beyond static, point-in-time benchmarks by running continuous tests across hundreds of chips and popular open-source frameworks. Free dashboard available here. ↗

Our benchmark has been widely reproduced, validated and/or supported by almost every major buyer ↗ of compute from Google Cloud ↗ to Microsoft Azure ↗ to Oracle, OpenAI ↗, and many more.

Evidence

InferenceXv2 builds on this foundation. It expands coverage to include large scale DeepSeek MoE disaggregated inference (disagg prefill, or simply “disagg”) with wide expert parallelism (wideEP) optimization to **all 6 NVIDIA western GPU SKUs from the past 4 years **as well as to every single AMD western GPU SKU released in the past 3 years

Context After

With today’s release, InferenceXv2 is now the first suite to benchmark the Blackwell Ultra GB300 NVL72 and B300 across the whole pareto frontier curve, and it is the first third party benchmark to test disagg+wideEP multi-node FP4 and FP8 MI355X performance. In future iterations of InferenceX, we will continue to focus heavily on disaggregated serving with wide expert parallelism as that is what is deployed in production at Frontier AI Labs like OpenAI, Anthropic, xAI, Google Deepmind, DeepSeek as well as advanced API providers like TogetherAI, Baseten, and Fireworks. In this article, we will also break down the system engineering principles and economics in play around the latest Claude Code Fast mode feature ↗.

Our benchmark is completely open-source under Apache 2.0 – this means that we are able to move at the same rapid speed at which the AI software ecosystem is advancing. If you like our work and would like to show us some support, please drop a star on our GitHub ↗! We also provide a free data visualizer at https://inferencex.com ↗ for everyone in the ML community to explore the complete dataset themselves.

② Atomic Claim

InferenceXv2 涵蓋過去三年間 AMD 在西方市場推出的所有 GPU SKUs。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/InferenceX",
        "label": "InferenceXv2"
      },
      "role": "benchmark"
    },
    {
      "node": {
        "id": "02_companies/AMD",
        "label": "AMD"
      },
      "role": "vendor"
    },
    {
      "node": {
        "id": "04_knowledge_base/GPU",
        "label": "GPU"
      },
      "role": "product_type"
    }
  ],
  "qualifiers": {
    "condition_text": "western GPU SKUs released in the past 3 years",
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "relation_type": "BENCHMARK_COVERAGE"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
benchmark	InferenceXv2	InferenceX
vendor	AMD	AMD
product_type	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。