IX2-0023
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Key Observations and Results to Highlight - Line hint:
39
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
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
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
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "UNSPECIFIED_ATTRIBUTE",
"context_nodes": [
{
"id": "04_knowledge_base/vLLM",
"label": "vLLM"
}
],
"entity": {
"id": "02_companies/AMD",
"label": "AMD"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "AMD 已淘汰自家較次級的 vLLM fork，轉向更接近 upstream，以改善使用體驗。"
}
}④ Canonical Entity Mapping
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。