IX2-0321
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Multi Token Prediction (MTP) - Line hint:
526
Context Before
Source: Brendan Bycroft ↗
This assumption regarding additional token production with the same time budget is strongest for dense models because batched verification can reuse the same weight stream across multiple positions. For Mixture-of-Experts models, different tokens may route to different experts, so verifying multiple draft tokens can activate more experts than single-token decoding and force additional expert weights to be fetched from memory. As shown in the Mixtral 8x7B Instruct model results in the EAGLE paper, this extra memory traffic erodes bandwidth savings and can make verification notably comparable to a standard decoding step.
Evidence
Multi-token prediction pursues similar benefits without requiring a separate draft model
Context After
Source: SemiAnalysis InferenceX ↗
② Atomic Claim
Multi-token prediction 追求類似效益，但不需要額外的 draft model。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"attribute": "UNSPECIFIED_ATTRIBUTE",
"context_nodes": [],
"entity": {
"id": "04_knowledge_base/Multi-Token Prediction",
"label": "Multi-token prediction"
},
"frame_type": "ATTRIBUTE",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
},
"value": {
"numeric_mentions": [],
"value_text": "Multi-token prediction 追求類似效益，但不需要額外的 draft model。"
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| entity | Multi-token prediction | 04_knowledge_base/Multi-Token Prediction |
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。