VR2R-0745_r1

VR2R-0745

① SA Source

• Source: 開啟完整 SA 文章
• Section: Groq LPU Decode Rack
• Line hint: 665

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.

Evidence

It will be designed to sit alongside Nvidia GPUs that handle decode for lower interactivity requests.

Context After

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.

② Atomic Claim

LPU system 的設計會與 Nvidia GPUs 並存；這些 GPUs 則負責較低 interactivity requests 的 decode。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/Groq LPU",
        "label": "LPU"
      },
      "role": "accelerator"
    },
    {
      "node": {
        "id": "02_companies/NVDA",
        "label": "Nvidia"
      },
      "role": "vendor"
    },
    {
      "node": {
        "id": "04_knowledge_base/GPU",
        "label": "GPU"
      },
      "role": "processor"
    },
    {
      "node": {
        "id": "04_knowledge_base/Decode",
        "label": "decode"
      },
      "role": "workload"
    }
  ],
  "qualifiers": {
    "condition_text": "Nvidia GPUs serve lower-interactivity decode requests",
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "relation_type": "LPU_COEXISTS_WITH_NVIDIA_GPU_DECODE_FOR_LOWER_INTERACTIVITY"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
accelerator	LPU	04_knowledge_base/Groq LPU
vendor	Nvidia	NVDA
processor	GPU	GPU
workload	decode	Decode

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。