VR2-0791
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Groq LPU Decode Rack - Line hint:
1001
Context Before
With CPX being designed specifically for inference pre-fill, the LPU system is designed for inference decode given the LPU’s emphasis on higher bandwidth SRAM. This comes at the expense of total throughput so this LPU decode system could be positioned at serving requests that require very high tokens per second per user, with the user paying much higher $/token to compensate for higher cost to serve.
It will be designed to sit alongside Nvidia GPUs that handle decode for lower interactivity requests. We have shared more details of the system specification to Accelerator Model clients, where we highlight one part of the supply chain that could be a big beneficiary ↗.
Evidence
there are 256 LPUs per rack
Context After
- 無
② Atomic Claim
關於 LPU：該 rack 內含 256 顆 LPUs。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "COUNT",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/Groq LPU",
"label": "LPU"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"256"
],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [
"256"
],
"value_text": "關於 LPU：該 rack 內含 256 顆 LPUs。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | LPU | 04_knowledge_base/Groq LPU |
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。