IX2-0465
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 decouples the inference engine from any specific transfer protocol and enables disaggregation across heterogeneous hardware where prefill and decode instances may span different device types or interconnects
Context After
② Atomic Claim
這使 inference engine 不必綁定特定 transfer protocol，也能支援 heterogeneous hardware 的 disaggregation，讓 prefill 與 decode instances 跨不同 device types 或 interconnects。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "04_knowledge_base/Inference engine",
"label": "inference engine"
},
"role": "supporting_subject"
},
{
"node": {
"id": "04_knowledge_base/Prefill",
"label": "prefill"
},
"role": "supported_entity"
},
{
"node": {
"id": "04_knowledge_base/Decode",
"label": "decode"
},
"role": "supported_entity"
}
],
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"relation_type": "SUPPORTS"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| supporting_subject | inference engine | 04_knowledge_base/Inference engine |
| supported_entity | prefill | Prefill |
| supported_entity | decode | Decode |
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。