IX2-0025

① SA Source

Context Before

Key Observations and Results to Highlight

We see competitive perf per TCO results on FP8 MI355X disagg+wideEP SGLang on AMD compared to FP8 B200 disagg+wideEP SGLang, but when compared to widely used Dynamo TRTLLM B200 FP8, TRT continues to framemog. This is amazing news that AMD SGLang Disagg prefill+wideEP for FP8 is able to match NVIDIA’s SGLang performance.

Evidence

Jensen needs to staff more resources & engineers towards contributing open ecosystems like SGLang & vLLM

Context After

SemiAnalysis InferenceX is free open source software and reader-supported. To receive new posts and support our work consider becoming a free or paid subscriber.

Subscribed

② Atomic Claim

SemiAnalysis 認為 Jensen 應配置更多資源與工程師,投入 SGLangvLLM 等開放 ecosystem。

  • Epistemic Mode: ASSERTED
  • Mapping Status: COMPLETE

③ Semantic Frame

{
  "additional_nodes": [],
  "frame_type": "RELATION",
  "object": {
    "id": "04_knowledge_base/vLLM",
    "label": "vLLM"
  },
  "predicate": "HAS_COMPONENT",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "subject": {
    "id": "04_knowledge_base/SGLang",
    "label": "SGLang"
  }
}

④ Canonical Entity Mapping

RoleSurface LabelCanonical Target
subjectSGLangSGLang
objectvLLMvLLM

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。