IX2-0464
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
Libraries like NIXL (NVIDIA Inference Transfer Library) abstract the data movement layer behind a unified asynchronous API with pluggable backends for UCX, GPUDirect Storage, and other transports
Context After
② Atomic Claim
像 NIXL（NVIDIA Inference Transfer Library）這類 library，透過統一 asynchronous API 抽象化 data-movement layer，並提供 UCX、GPUDirect Storage 與其他 transports 的 pluggable backends。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "04_knowledge_base/NVIDIA Inference Xfer Library (NIXL)",
"label": "NIXL"
},
"role": "subject"
},
{
"node": {
"id": "02_companies/NVDA",
"label": "NVIDIA"
},
"role": "participant"
},
{
"node": {
"id": "04_knowledge_base/UCX communication framework",
"label": "UCX"
},
"role": "participant"
},
{
"node": {
"id": "04_knowledge_base/GPUDirect Storage",
"label": "GPUDirect Storage"
},
"role": "participant"
}
],
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"relation_type": "PROVIDES"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| subject | NIXL | 04_knowledge_base/NVIDIA Inference Xfer Library (NIXL) |
| participant | NVIDIA | NVDA |
| participant | UCX | 04_knowledge_base/UCX communication framework |
| participant | GPUDirect Storage | 04_knowledge_base/GPUDirect Storage |
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。