IX2-0581
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Migration to Multi Turn Real Multi-Turn Chat and Agentic Coding Datasets - Line hint:
808
Context Before
Migration to Multi Turn Real Multi-Turn Chat and Agentic Coding Datasets
Currently, InferenceX uses completely random tokens as input for benchmarking. We then vary the ISL/OSL uniformly subject to the distribution [ISL*0.8, ISL], similarly for OSL. Because of the random data, we disable prefix caching in all our benchmarks, as the expected value of a prefix cache hit rate on completely random data is 0%. Furthermore, all the random data is single-turn, meaning each conversation contains only one prompt and one response. While this provides a good baseline Pareto frontier, it is not a practical benchmark setup that mimics real-world production inference workloads.
Evidence
In addition to enabling prefix caching on all scenarios, we will enable KV cache CPU offloading, as this is what we see being done in production workloads
Context After
The point is: real-world multiturn datasets test more SOTA inference engine features and can capture more nuanced and robust performance data across all chips.
With the rise of Claude Code, Codex, and Kimi, it is becoming increasingly important to benchmark performance in agentic coding scenarios. Like above, these scenarios are multi-turn but also include extremely long context conversations as well as tool use. In the next few months, we plan on creating a benchmark suite that will most accurately capture the performance of open models in these agentic coding scenarios across all chips.
② Atomic Claim
除了在所有情境啟用 prefix caching 外，團隊也計畫啟用 KV cache CPU offloading，因為這是 production workloads 中實際採用的做法。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "04_knowledge_base/Prefix Caching",
"label": "prefix caching"
},
"role": "user_or_subject"
},
{
"node": {
"id": "04_knowledge_base/KV cache",
"label": "KV cache"
},
"role": "used_entity"
},
{
"node": {
"id": "04_knowledge_base/CPU",
"label": "CPU"
},
"role": "used_entity"
}
],
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"relation_type": "USES"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| user_or_subject | prefix caching | 04_knowledge_base/Prefix Caching |
| used_entity | KV cache | 04_knowledge_base/KV cache |
| used_entity | 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。