IX2-0509
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Dive into DeepSeek R1 Single Node Results - Line hint:
714
Context Before
On DeepSeek R1 FP8 1k1k, we see that MI355X is competitive with its counterpart B200 on single node scenarios, despite getting mogged on FP4 multi node scenarios. MI355X (SGLang) even beats B200 (SGLang) in throughput performance at lower interactivity levels. Moreover, MI355X (SGLang) beats B200 (TRT and SGLang) in most cases from a perf/TCO perspective.
Unfortunately, the year is 2026, and most frontier labs and inference providers are not running FP8 nor single node inference.
Evidence
Speed is the moat
Context After
Source: SemiAnalysis InferenceX ↗
② Atomic Claim
關於 DeepSeek R1：速度就是護城河。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "UNSPECIFIED_ATTRIBUTE",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/DeepSeek R1",
"label": "DeepSeek R1"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "關於 DeepSeek R1：速度就是護城河。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | DeepSeek R1 | 04_knowledge_base/DeepSeek R1 |
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。