NIEK2-0293
① SA Source
- Source: 開啟完整 SA 文章
- Section:
CMX - Line hint:
367
Context Before
CMX
CMX is NVIDIA’s context memory storage platform. CMX addresses a growing bottleneck in modern inference infrastructure: the rapid expansion of KV Cache required to support long-context and agentic workloads.
Evidence
KV cache grows linearly with input sequence length and number of users
Context After
NVIDIA introduced a “new” intermediate storage “tier G3.5” within the inference memory hierarchy at CES in January. Tier G3.5 NVMe sits in between tier G3 DRAM and tier G4 shared storage (also NVMe, or SATA/SAS SSD, or HDD). Previously referred to as ICMS (Inference Context Memory Storage) and now branded as the CMX platform, this is just another re-brand of storage servers attached to compute servers via Bluefield NICs. The only difference from NVMe architectures is the swap from Connect-X NICs to Bluefield NICs.
② Atomic Claim
KV cache 會隨輸入 sequence length 與使用者數量線性成長。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"additional_nodes": [],
"frame_type": "RELATION",
"object": {
"id": "04_knowledge_base/Sequence length",
"label": "sequence length"
},
"predicate": "USES",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"subject": {
"id": "04_knowledge_base/KV cache",
"label": "KV cache"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| subject | KV cache | 04_knowledge_base/KV cache |
| object | sequence length | 04_knowledge_base/Sequence length |
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。