clm_377cbcbcb6104040a5beca7c0fba9b9d_r1

IX2-0294

① SA Source

• Source: 開啟完整 SA 文章
• Section: AMD ATOM Engine
• Line hint: 494

Context Before

Source: SemiAnalysis InferenceX ↗

AMD ATOM Engine

Evidence

One such example is that it does not support NVMe or CPU KVCache offloading, tool parsing, wide expert parallelism, or disaggregated serving

Context After

Furthermore, maintainers of open-source inference engines like vLLM are disappointed in AMD due to a lack of engineering and GPU resources provided by AMD. For example, Simon Mo, lead vLLM maintainer, states in this GitHub RFC that there is still no working MI355X that he can add to vLLM CI, hence the poor user experience. There are currently zero Mi355X tests on vLLM, while NVIDIA’s B200 has many tests on vLLM. Similarly, there are still not enough MI300X CI machines on vLLM. Upstream vLLM needs at least 20 more MI300 machines, 20 more MI325 machines and 20 more MI355X machines to reach the same level of usability as CUDA.

We at SemiAnalysis have been trying to get AMD to contribute more compute to vLLM and have had some success on that within the couple weeks. vLLM will start to get a couple of MI355X machines such that they can bring their CI test parity from 0% to non-0%. We will talk more about AMD’s previous lackluster contribution towards vLLM, SGLang, PyTorch CI machine situation & how Anush started to fix it in our upcoming State of AMD article. At SemiAnalysis, we will have internal dashboard to track the # of tests & quality of tests that AMD & NVIDIA runs on vLLM, SGLang, PyTorch, & JAX.

② Atomic Claim

例如 ATOM 不支援 NVMe 或 CPU KVCache offloading、tool parsing、wide expert parallelism 或 disaggregated serving。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/NVMe",
        "label": "NVMe"
      },
      "role": "supporting_subject"
    },
    {
      "node": {
        "id": "04_knowledge_base/CPU",
        "label": "CPU"
      },
      "role": "supported_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/KV cache",
        "label": "KVCache"
      },
      "role": "supported_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/Expert Parallelism",
        "label": "wide expert parallelism"
      },
      "role": "supported_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/Disaggregated serving",
        "label": "disaggregated serving"
      },
      "role": "supported_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/AMD ATOM inference engine",
        "label": "ATOM"
      },
      "role": "context_entity"
    }
  ],
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "relation_type": "SUPPORTS"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
supporting_subject	NVMe	NVMe
supported_entity	CPU	CPU
supported_entity	KVCache	04_knowledge_base/KV cache
supported_entity	wide expert parallelism	04_knowledge_base/Expert Parallelism
supported_entity	disaggregated serving	04_knowledge_base/Disaggregated serving
context_entity	ATOM	04_knowledge_base/AMD ATOM inference engine

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。