English(EN) TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training Quantization

TileQuant框架优化LLM量化以实现更快的推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员开发了TileQuant，一个新颖的训练后量化框架，旨在通过在瓦片级别分配精度来优化大型语言模型（LLM）的部署。该方法分析二维瓦片内的权重敏感性，允许关键瓦片使用更高精度，而其他瓦片使用较低精度，从而在不显著降低质量的情况下减少计算开销。实验表明，TileQuant可以将生成吞吐量提高高达2.66倍，同时在各种语言任务中保持或提高性能。 AI

影响能够更有效地部署大型语言模型，可能降低成本并提高推理速度。

排序理由详细介绍LLM量化新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM量化新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Feng · 2026-11-06 05:00

TileQuant：以Tile作为LLM混合精度训练后量化的精度分配单元

arXiv:2611.07217v1 Announce Type: cross Abstract: Post-training quantization (PTQ) reduces large language model (LLM) deployment costs, but preserving quality requires accounting for uneven weight sensitivity. Uniform PTQ uses one weight bit-width, importance-aware PTQ adjusts sc…

本文如何被排名

报道来源 [1]

TileQuant：以Tile作为LLM混合精度训练后量化的精度分配单元

相关实体

相关话题