arXiv Machine Learning July 17, 2026 By Hyunwoo Oh, Suyeon Jang, Hanning Chen, KyungIn Nam, Sanggeon Yun, Ryozo Masukawa, Mohsen Imani

PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference

Read the original on arXiv Machine Learning →

arXiv:2607. 14618v1 Announce Type: new Abstract: CPUs are the most universal target for on-device LLM inference, but existing low-bit quantization methods offer either coarse operating points or fine-grained mixed precision that is difficult to execute efficiently on CPUs.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 6

Channel-Wise Mixed-Precision Quantization for Large Language Models

arXiv:2410. 13056v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remains challenging due to the substantial memory requirements imposed by their large parameter sizes.

By Zihan Chen, Bike Xie, Jundong Li, Cong Shen

llms efficiency

arXiv AI

Jun 4

dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats

arXiv:2606. 04115v1 Announce Type: cross Abstract: Quantizing large language models (LLMs) to low-precision floating-point representations is central to efficient deployment, yet applying a single bit-width uniformly across all layers is sub-optimal in terms of both performance and accuracy.

By Giuseppe Franco, Ian Colbert, Pablo Monteagudo-Lago, Felix Marty, Nicholas Fraser

llms efficiency benchmarks

arXiv AI

Jun 4

LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection

arXiv:2606. 04050v1 Announce Type: cross Abstract: Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.

By Liulu He, XuanAng Liu, Juntao Liu, Taolue Feng, Ting Lu, Chunsheng Gan, Zhiyv Peng, Yuan Du, Huanrui Yang, Yijiang Liu, Li Du

llms efficiency benchmarks

arXiv Machine Learning

Jun 29

RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory

arXiv:2605. 06675v2 Announce Type: replace Abstract: Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottleneck for serving.

By Fei Zuo, Zikang Zhou, Hao Cong, Xiaoyan Xi, Ho Fai Leung

llms efficiency

arXiv Machine Learning

Jul 7

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models

arXiv:2607. 02893v1 Announce Type: new Abstract: Low-bit quantization shrinks language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width.

By Hamish Ogilvy

llms efficiency

arXiv AI

Jun 2

BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization

arXiv:2606. 00079v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory.

By Jiayu Zhao, Zihan Teng, Minhao Fan, Tianrui Ma, Wentao Ren, Song Chen, Weichen Liu

llms efficiency

Related stories

Channel-Wise Mixed-Precision Quantization for Large Language Models

dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats

LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection

RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models

BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization