IX2-0515
① SA Source
- Source: 開啟完整 SA 文章
- Section:
GPT-OSS 120B Single Node - Line hint:
740
Context Before
Source: SemiAnalysis InferenceX ↗
GPT-OSS 120B Single Node
Evidence
Context After
Above that tier sits NVIDIA’s B200 and GB200, which outperform MI355X across the frontier. While B200 and GB200 share the same Blackwell compute die, GB200 achieves a higher throughput–interactivity curve because the platform and serving stack reduce non-compute bottlenecks at scale (interconnect/topology, CPU-GPU coupling, and runtime scheduling), translating into effective scale-out and less overhead per token.
② Atomic Claim
在 throughput 對 interactivity 圖中，MI300X、MI325X、H200 與 H100 聚集於左下區域，代表整體 trade-off 類似，而 Nvidia 通常略占優勢。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "THROUGHPUT",
"context_nodes": [
{
"id": "04_knowledge_base/MI325X",
"label": "MI325X"
},
{
"id": "04_knowledge_base/H200",
"label": "H200"
},
{
"id": "04_knowledge_base/H100",
"label": "H100"
},
{
"id": "02_companies/NVDA",
"label": "Nvidia"
}
],
"entity": {
"id": "04_knowledge_base/MI300X",
"label": "MI300X"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "在 throughput 對 interactivity 圖中，MI300X、MI325X、H200 與 H100 聚集於左下區域，代表整體 trade-off 類似，而 Nvidia 通常略占優勢。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | MI300X | MI300X |
| context_0 | MI325X | MI325X |
| context_1 | H200 | H200 |
| context_2 | H100 | H100 |
| context_3 | Nvidia | NVDA |
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。