IX2-0153
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Nvidia versus AMD Disagg Prefill - Line hint:
258
Context Before
Source: SemiAnalysis InferenceX ↗
Nvidia versus AMD Disagg Prefill
Evidence
With today’s release of InferenceXv2, for the first time the ML community is able to see a full Pareto frontier for open-source MI355X distributed inference
Context After
For FP8 disagg prefill, MI355X (MoRI SGLang) is quite competitive with B200 (Dynamo SGLang). Wide EP is not used for either of these configs as all prefill/decode instances run using EP8 at the most. At both ends of the throughput versus interactivity Pareto frontier, MI355X falls behind the B200 slightly. However, MI355X disagg has a slight advantage for certain levels of interactivity in the middle of the curve. Both the B200 and the MI355X benefit from employing MTP, and we observe the same relative performance improvement for both chips when using MTP.
② Atomic Claim
隨著 InferenceXv2 發布，ML 社群首次能看到開源 MI355X distributed inference 的完整 Pareto frontier。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"additional_nodes": [],
"frame_type": "RELATION",
"object": {
"id": "04_knowledge_base/MI355X",
"label": "MI355X"
},
"predicate": "INTRODUCES",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"subject": {
"id": "04_knowledge_base/InferenceX",
"label": "InferenceXv2"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| subject | InferenceXv2 | InferenceX |
| object | MI355X | MI355X |
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。