IX2-0037
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Key Observations and Results to Highlight - Line hint:
51
Context Before
Turning to AMD, we find that the biggest issue with inference on their systems and using their software is composability ↗. That is, many of AMDs inference optimization implementations work well in isolation, but when combined with other optimizations, the result is not as competitive as one would expect. Specifically, the composability of disagg prefill, wideEP and FP4 inference optimizations needs significant improvement.
While performance is competitive on AMD when enabling just a subset of the SOTA inference optimizations, enabling all three major optimizations that labs use, AMD’s performance is currently not competitive with Nvidia’s. We strongly recommend to AMD that they focus heavily on composability of different inference optimizations. We have been told that AMD will start focusing on software composability of FP4+distributed inferencing across their whole software stack. This will happen after Chinese New Year as most of their disagg prefill+wideEP 10x inference engineers are based in China
Evidence
On H100 vs GB200 NVL72, we see up to 55x realized performance difference at 75 tok/s/user
Context After
At GTC 2024, Jensen claimed that Blackwell will deliver up to 30x perf on inference compared to H100, Jensen under promised & overdelivered on Blackwell inference performance. This should curtail the instances of analysts cracking “Jensen Math” jokes for some time.
② Atomic Claim
比較 H100 與 GB200 NVL72，在 75 tok/s/user 下可觀察到最高 55 倍的實際效能差距。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"comparison_expression": "比較 H100 與 GB200 NVL72，在 75 tok/s/user 下可觀察到最高 55 倍的實際效能差距。",
"entities": [
{
"id": "04_knowledge_base/H100",
"label": "H100"
},
{
"id": "04_knowledge_base/GB200 NVL72",
"label": "GB200 NVL72"
}
],
"frame_type": "COMPARISON",
"metric": "THROUGHPUT",
"operator": "MULTIPLE_OF",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"75 tok/s/user",
"55"
],
"temporal_mentions": []
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| comparison_entity_0 | H100 | H100 |
| comparison_entity_1 | GB200 NVL72 | 04_knowledge_base/GB200 NVL72 |
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。