IX2-0537

① SA Source

Context Before

Core Changes Since InferenceXv1

One of the main changes we have made since v1 is the cadence with which we perform sweeps. Previously, we were jestermaxing and performed a full sweep over each configuration nightly. However, as we added more chips, disaggregated prefill, wide EP, and other features, we realized that running every single night was way too time consuming and wasteful. Moreover, it’s just not necessary – benchmarks only really need to be re-run when recipes change or a new software version is released.

Evidence

The jobs collect all data points for the full sweep and upload the results as artifacts

Context After

Below is a high-level diagram of how InferenceX launches jobs.

image

② Atomic Claim

關於 InferenceX:這些 jobs 會收集完整 sweep 的所有 data points,並把結果上傳為 artifacts。

  • Epistemic Mode: ASSERTED
  • Mapping Status: PARTIAL

③ Semantic Frame

{
  "attribute": "UNSPECIFIED_ATTRIBUTE",
  "context_nodes": [],
  "entity": {
    "id": "04_knowledge_base/InferenceX",
    "label": "InferenceX"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "關於 InferenceX:這些 jobs 會收集完整 sweep 的所有 data points,並把結果上傳為 artifacts。"
  }
}

④ Canonical Entity Mapping

RoleSurface LabelCanonical Target
entityInferenceXInferenceX

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。