clm_4a2b4e4effb24238baeda06a860f4fc5_r1

VR2-0786

① SA Source

• Source: 開啟完整 SA 文章
• Section: Groq LPU Decode Rack
• Line hint: 997

Context Before

Groq LPU Decode Rack

Since Nvidia acquired Groq entered into a licensing agreement for Groq’s technology and hired Groq’s key people December 2025, speculation has brewed on how exactly Nvidia will implement Groq’s technology. We believe that Nvidia will introduce a new LPU rack at GTC 2026. The LPU rack is designed to be used alongside Nvidia GPUs for inference.

Evidence

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

Context After

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 ↗.

Some details we will share here is that there are 256 LPUs per rack and it is the 3rd generation Groq chip on Samsung 4nm (the 2nd generation is being skipped). We share an important supply chain detail that has an impact on growth and market share as well as topology in the Accelerator Model note. ↗

② Atomic Claim

CPX 專為 inference pre-fill 設計；LPU system 則因 LPU 強調高 bandwidth SRAM，定位在 inference decode。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/CPX High-Density Interconnect Paradigm",
        "label": "CPX"
      },
      "role": "endpoint_or_system"
    },
    {
      "node": {
        "id": "04_knowledge_base/Groq LPU",
        "label": "LPU"
      },
      "role": "connected_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/SRAM",
        "label": "SRAM"
      },
      "role": "connected_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/Decode",
        "label": "decode"
      },
      "role": "connected_entity"
    }
  ],
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "relation_type": "CONNECTS_TO"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
endpoint_or_system	CPX	04_knowledge_base/CPX High-Density Interconnect Paradigm
connected_entity	LPU	04_knowledge_base/Groq LPU
connected_entity	SRAM	SRAM
connected_entity	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。