VR2R-0728
① SA Source
- Source: 開啟完整 SA 文章
- Section:
VR NVL72 TCO: BoM and Power Budget Analysis - Line hint:
637
Context Before
As always, one caveat is that this comparison is done based on a marketed dense PFLOP basis. Effective dense PFLOP (i.e. the real world chip throughput) can differ based on Model Flops Utilization % (MFU), and in general we have seen NVIDIA chip operate at a higher MFU % vs AMD chips, suggesting that performance per TCO based on effective dense PFLOPs could be better for NVIDIA systems vs AMD—however, MFU is dependent on actual workloads with no one-size-fits-all MFU % that is consistently applicable to either systems.
Evidence
Context After
but it will probably deliver better effective FLOPs than FP4 Dense, but we have yet to evaluate what that real-world performance could be. Running VR NVL72 on 1800W would probably mean lower FP4 Sparse FLOPs than on 2300W.
② Atomic Claim
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "04_knowledge_base/FP4",
"label": "FP4"
},
"role": "datatype"
},
{
"node": {
"id": "04_knowledge_base/Sparsity",
"label": "Sparsity"
},
"role": "feature"
}
],
"qualifiers": {
"condition_text": "real-world usage expectation",
"numeric_mentions": [
"50 PFLOPS"
],
"temporal_mentions": []
},
"relation_type": "REAL_WORLD_FP4_SPARSITY_BELOW_MARKETED_50_PFLOPS"
}④ Canonical Entity Mapping
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。