VR2R-0731
① SA Source
- Source: 開啟完整 SA 文章
- Section:
VR NVL72 TCO: BoM and Power Budget Analysis - Line hint:
981
Context Before
Source: SemiAnalysis AI TCO Model ↗
Evidence
Inference throughput too can diverge materially from marketed peak FLOPS, meaning spec-sheet compute does not directly translate into real-world token generation performance. While the B300 is rated at 4,500 Dense FP8 TFLOPs versus 5,000 Dense FP8 TFLOPs for MI355, implying a 10% theoretical compute disadvantage and with same marketed memory bandwidth of 8TB/s measured inference token throughput from our InferenceX ↗ benchmarks shows B300 delivering roughly 6.3x the performance at 100 interactivity for Deepseek R1, using 8k input tokens and 1k output tokens.
Context After
Given that total cost of ownership is only 1.75x higher, this results in a superior performance-per-TCO profile for B300 despite the more modest marketed figures. Such a wildly different result despite very similar specs underscores that real world performance is not dictated by peak FLOPS or memory bandwidth alone. Software and network capabilities are also major factors that contribute to training and token throughput in real workloads.
Rubin and MI4XX will ship with new microarchitectures, real world performance is especially difficult to predict without and benchmarking like we do with InferenceX.
② Atomic Claim
inference throughput 也可能和 marketed peak FLOPS 有顯著差異，因此規格表上的 compute performance 並不會直接轉化成真實世界的 token generation performance。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"frame_type": "CLAIM_ONLY",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"reason": "GENERAL_PERFORMANCE_PRINCIPLE_WITHOUT_EXPLICIT_CANONICAL_SUBJECT",
"statement": "Inference throughput can materially diverge from marketed peak FLOPS, so spec-sheet compute does not directly translate to real-world token-generation performance."
}④ Canonical Entity Mapping
- 此
CLAIM_ONLYrevision 沒有 canonical Entity mapping。
⑤ V2 Draft（需要修正時直接編輯）
Inline repair
只編輯以下三個 Draft 區塊。完成後將
review_action設為REQUEST_REPAIR，再手動執行 Repair Preview。
執行腳本前，Draft 不會寫入 Claim Store 或 Graph。
V2 Atomic Claim Draft
inference throughput 也可能和 marketed peak FLOPS 有顯著差異，因此規格表上的 compute performance 並不會直接轉化成真實世界的 token generation performance。
V2 Semantic Frame Draft
{
"frame_type": "CLAIM_ONLY",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"reason": "GENERAL_PERFORMANCE_PRINCIPLE_WITHOUT_EXPLICIT_CANONICAL_SUBJECT",
"statement": "Inference throughput can materially diverge from marketed peak FLOPS, so spec-sheet compute does not directly translate to real-world token-generation performance."
}V2 Revision Metadata Draft
{
"epistemic_mode": "ASSERTED",
"mapping_status": "PARTIAL"
}⑥ 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。