IX2-0030
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Key Observations and Results to Highlight - Line hint:
47
Context Before
Subscribed
When it comes to the latest inference techniques that are used by the most prominent frontier large-scale inference services (such as disagg prefill+wideEP+FP4), Nvidia absolutely frame mogs with the B200, B300 and ASU frat leader, rack scale GB200/GB300 NVL72 across both SGLang and TRTLLM. Nvidia GPUs also dominate when it comes to energy efficiency, with much lower all-in provisioned picoJoules of energy per token across all workloads.
Evidence
Specifically, the composability of disagg prefill, wideEP and FP4 inference optimizations needs significant improvement
Context After
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
Nvidia’s GB300 NVL72 doesn’t disappoint. It achieves up to 100x on FP8 vs FP4 compared to even a strong H100 disagg+wideEP+MTP baseline and 65x on FP8 vs FP8. On H100 vs GB200 NVL72, we see up to 55x realized performance difference at 75 tok/s/user. Rack scale Blackwell NVL72 is framemogging hopper and makes hopper looks like it is jestermaxxing. As Jensen said at GTC 2025, he is chief revenue destroyer. ↗
② Atomic Claim
尤其 disagg prefill、wideEP 與 FP4 inference 等最佳化之間的 composability 仍需要大幅改善。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"attribute": "COMPOSABILITY",
"context_nodes": [
{
"id": "04_knowledge_base/FP4",
"label": "FP4 inference"
}
],
"entity": {
"id": "04_knowledge_base/Prefill",
"label": "prefill"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "尤其 disagg prefill、wideEP 與 FP4 inference 等最佳化之間的 composability 仍需要大幅改善。"
}
}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。