SA260324R-0062_r1

SA260324R-0062

① SA Source

• Source: 開啟完整 SA 文章
• Section: SRAM and Memory Hierarchy
• Line hint: 71

Context Before

SRAM machines such as Groq’s LPU therefore enable very fast time to first token and tokens per second per user but at the expense of total throughput, as their limited SRAM capacity quickly gets saturated by weights, with little left over for KVcache that grows as more users are batched. GPUs win for throughput and cost as we have shown.

Evidence

This is why Nvidia has decided to combine these architectures to get the best of both worlds: accelerate parts of decode that are more latency sensitive

Context After

and are not as memory heavy on a low-latency SRAM-heavy chip like the LPU, while memory hungry attention is performed on GPUs that come with a lot of fast (but not SRAM fast) memory capacity.

② Atomic Claim

因此 Nvidia 決定結合兩種架構，以加速 decode 中對延遲較敏感的部分。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "LATENCY",
  "context_nodes": [
    {
      "id": "04_knowledge_base/Decode",
      "label": "decode"
    }
  ],
  "entity": {
    "id": "02_companies/NVDA",
    "label": "Nvidia"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "因此 Nvidia 決定結合兩種架構，以加速 decode 中對延遲較敏感的部分。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	Nvidia	NVDA
context_node	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。