IX2-0282
① SA Source
- Source: 開啟完整 SA 文章
- Section:
AMD Composability Issue on FP4, Distributed Inferencing and Wide Expert Parallelism - Line hint:
480
Context Before
AMD Composability Issue on FP4, Distributed Inferencing and Wide Expert Parallelism
While AMD performs somewhat decently on single node FP4 and performs competitively to B200 SGLang on FP8 distributed inferencing, the issue with the current AMD open source inferencing stack is that, while individual inference optimizations perform well, real customers deploy with multiple optimizations composed together. Top tier AI labs are all using FP4 **with **disaggregated inferencing with wide expert parallelism all enabled at the same time, and this is where the issue occurs.
Evidence
SemiAnalysis is free open source software and reader-supported
Context After
Subscribed
AMD software is still not meeting the mark, and the theoretical speed of light modelling at SemiAnalysis and at AMD show that for FP4, disaggregated inferencing with wide expert parallelism should perform better than inference on a single node of MI355X. Unfortunately, Software continues to be a massive bottleneck for AMD GPUs. AMD management needs to continue to sharpen resource allocation of their engineering talent, for instance, re-allocate their engineering resources away from pet single node projects that nobody uses like ATOM towards fixing the aforementioned issues with composability of inference optimizations between disaggregated inferencing, wide expert parallelism and FP4. The current subpar software is due to lack of focus and incorrect prioritization of where the industry already is at. All top tier labs are already using disaggregated inferencing and wide expert parallelism; AMD needs to stop focusing on single node and heavily invest focus into multi node inferencing for open source solutions.
② Atomic Claim
SemiAnalysis 的相關軟體為免費開源，並由讀者支持。
- Epistemic Mode:
ASSERTED - Mapping Status:
CLAIM_ONLY
③ Semantic Frame
{
"frame_type": "CLAIM_ONLY",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"reason": "NO_NODE_REQUIRED",
"statement": "SemiAnalysis 的相關軟體為免費開源，並由讀者支持。"
}④ Canonical Entity Mapping
- 此
CLAIM_ONLYrevision 沒有 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。