IX2-0019
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Key Observations and Results to Highlight - Line hint:
37
Context Before
Source: InferenceMAX GitHub ↗
Key Observations and Results to Highlight
Evidence
Context After
We also see that for single node aggregated serving, AMD’s SGLang delivers better perf per TCO than NVIDIA’s SGLang for FP8. It is also great to see that AMD has deprecated their second class fork of vllm to move further upstream and closer to delivering first class experience. ↗ Stay tuned for our “State of AMD” article where we talk about the many areas where AMD’s pace of improvement has been rapid & also the areas where the pace of improvement has been lackluster. We recommend that NVIDIA focus even more on SGLang & vLLM ecosystem in addition their TRTLLM engine. Jensen needs to staff more resources & engineers towards contributing open ecosystems like SGLang & vLLM ↗.
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.
② Atomic Claim
在 AMD 上以 SGLang 執行 FP8 MI355X disagg+wideEP，其每單位 TCO 效能相較 B200 FP8 disagg+wideEP SGLang 已具競爭力。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"comparison_expression": "在 AMD 上以 SGLang 執行 FP8 MI355X disagg+wideEP，其每單位 TCO 效能相較 B200 FP8 disagg+wideEP SGLang 已具競爭力。",
"entities": [
{
"id": "02_companies/AMD",
"label": "AMD"
},
{
"id": "04_knowledge_base/SGLang",
"label": "SGLang"
},
{
"id": "04_knowledge_base/FP8",
"label": "FP8"
},
{
"id": "04_knowledge_base/MI355X",
"label": "MI355X"
},
{
"id": "04_knowledge_base/NVIDIA B200",
"label": "B200"
}
],
"frame_type": "COMPARISON",
"metric": "COST",
"operator": "COMPARES_WITH",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| comparison_entity_0 | AMD | AMD |
| comparison_entity_1 | SGLang | SGLang |
| comparison_entity_2 | FP8 | FP8 |
| comparison_entity_3 | MI355X | MI355X |
| comparison_entity_4 | B200 | 04_knowledge_base/NVIDIA B200 |
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。