IX2-0132
① SA Source
- Source: 開啟完整 SA 文章
- Section:
DeepSeek Disagg +WideEP Results Deep Dive - Line hint:
204
Context Before
NVIDIA uses Dynamo for its disaggregated inference setup. Dynamo ↗ is an inference framework designed for multi-node distributed inference, featuring techniques such as prefill-decode disaggregation, request routing, and KV cache offloading. It is inference-engine agnostic, allowing us to use SGLang and TRT LLM as backends in our benchmark. For AMD, we use SGLang with two different KV cache transfer frameworks: MoRI and Mooncake. MoRI ↗ is a high-performance communication interface focusing on RDMA and GPU integration, offering applications such as network collective operations and expert parallel kernels. Mooncake, which recently joined the PyTorch ecosystem ↗, supports prefill-decode disaggregation and many fault tolerant multi-node features.
DeepSeek Disagg +WideEP Results Deep Dive
Evidence
At almost all interactivity levels, disagg outperform aggregated inference (grey lines) in terms of total token throughput per GPU
Context After
Source: SemiAnalysis InferenceX ↗
② Atomic Claim
在幾乎所有 interactivity 水準下，disagg 的每 GPU 總 token throughput 都優於 aggregated inference（灰線）。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"comparison_expression": "在幾乎所有 interactivity 水準下，disagg 的每 GPU 總 token throughput 都優於 aggregated inference（灰線）。",
"entities": [
{
"id": "04_knowledge_base/GPU",
"label": "GPU"
}
],
"frame_type": "COMPARISON",
"metric": "THROUGHPUT",
"operator": "OUTPERFORMS",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| comparison_entity_0 | GPU | GPU |
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。