---
id: 20260321-T0-09
title: "MineDraft：批并行推测解码框架提升推理效率"
title_en: "MineDraft Framework Boosts Inference via Batch Parallel Speculative Decoding"
url: https://ai.daily.yangsir.net/daily/20260321-T0-09
issue_date: 2026-03-21
publish_date: 2026-03-20T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2603.18016
---

# MineDraft：批并行推测解码框架提升推理效率

arXiv论文提出MineDraft框架，通过批并行推测解码加速大模型推理。传统推测解码受严格同步限制，而新方法使用较小模型生成多个并行候选序列，由目标模型验证，显著提升吞吐量。该方案在保持准确率的同时，将推理速度提升30%以上。

## English Version

**MineDraft Framework Boosts Inference via Batch Parallel Speculative Decoding**

arXiv paper introduces MineDraft, a framework that accelerates LLM inference via batch parallel speculative decoding. Traditional SD is limited by strict synchronization, but this method uses a smaller model to generate multiple parallel candidate sequences verified by the target model, boosting throughput by over 30% while maintaining accuracy.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2603.18016)

**详情页**：https://ai.daily.yangsir.net/daily/20260321-T0-09

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*