IX2-0463
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Disaggregated Prefill - Line hint:
672
Context Before
Source: DistServe ↗
Disaggregation also enables independent scaling and optimization of each phase. With separate nodes, each phase can be tuned independently: different parallelism strategies, different batch sizes, and different memory allocation ratios. The ratio of prefill to decode nodes can also be matched to the workload’s input-output length ratio. For instance, prefill-dominated workloads (long input, short output e.g., summarization, RAG, agentic coding with large context windows) allocate more prefill instances. Decode-dominated workloads (short input, long output e.g., chain-of-thought reasoning, long-form generation) allocate more decode instances. Workloads with high cache hit rates also tend toward more decode, since reused KV cache entries from shared system prompts or multi-turn conversation history skip prefill entirely.
Evidence
This transfer is performed over RDMA (typically RoCE or InfiniBand) using zero-copy GPU-to-GPU data movement without CPU involvement
Context After
② Atomic Claim
這項傳輸透過 RDMA，通常是 RoCE 或 InfiniBand，以 zero-copy GPU-to-GPU data movement 完成，不需要 CPU 參與。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "UNSPECIFIED_ATTRIBUTE",
"context_nodes": [
{
"id": "04_knowledge_base/InfiniBand",
"label": "InfiniBand"
},
{
"id": "04_knowledge_base/GPU",
"label": "GPU"
},
{
"id": "04_knowledge_base/CPU",
"label": "CPU"
}
],
"entity": {
"id": "04_knowledge_base/RDMA",
"label": "RDMA"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "這項傳輸透過 RDMA，通常是 RoCE 或 InfiniBand，以 zero-copy GPU-to-GPU data movement 完成，不需要 CPU 參與。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | RDMA | RDMA |
| context_0 | InfiniBand | InfiniBand |
| context_1 | GPU | GPU |
| context_2 | CPU | CPU |
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。