IX2-0371
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Anthropic Fast Mode Inferencing Explained - Line hint:
594
Context Before
Source: SemiAnalysis InferenceX ↗
Evidence
This follows directly from the fundamental latency-throughput tradeoff in LLM inference. At high batch sizes, GPUs achieve better utilization and greater total token throughput, meaning more users served concurrently and lower cost per token. At low batch sizes with greater parallelism per request, each user gets faster responses, but total token throughput drops. Since the hourly cost of the accelerators ↗ is fixed regardless of how they’re used, lower throughput means fewer tokens over which to amortize that cost, and thus a higher price per token.
Context After
In short, fast mode isn’t necessarily a hardware story, but merely the natural consequence of trading throughput for latency on the same GPUs.
② Atomic Claim
關於 Anthropic：由於 accelerators 每小時成本不會因使用方式改變，throughput 越低，可分攤固定成本的 tokens 越少，因此每 token 價格越高。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "THROUGHPUT",
"context_nodes": [],
"entity": {
"id": "02_companies/Anthropic",
"label": "Anthropic"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "關於 Anthropic：由於 accelerators 每小時成本不會因使用方式改變，throughput 越低，可分攤固定成本的 tokens 越少，因此每 token 價格越高。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | Anthropic | Anthropic |
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。