arXiv AI By Jiatong Ding, Bingxin Xing, Yu Zhang, Dian Ding, Xiaodong Yi, Xianbin Ouyang, Feihu Zhou, Kun Zhang, Zhenyu Guo, Hao Pan, Guangtao Xue, Yiming Zhang

HyQuant: Hybrid-Precision Quantization for LLM Attention

Read the original on arXiv AI →

HyQuant introduces a hybrid-precision quantization framework for large language model (LLM) attention modules. It quantizes most attention states to low-bit formats while preserving a small set of vertical‑line tokens and local‑window states in full precision, guided by lightweight attention‑pattern signals. This design achieves near‑lossless accuracy across tasks while improving memory and hardware efficiency.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
Jul 1

RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference

arXiv:2606. 31519v1 Announce Type: new Abstract: Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budget (Top-k) retrieval or rely on proxy scores that are computationally expensive and biased.

By Wenhao Li, Jinhao Dong, Hailin Zhang, Wenhang Shi, Wei Lu, Xiaoyong Du
arXiv Machine Learning
4d ago

Attention Quantization for Tabular Foundation Models

The paper introduces a quantization technique for tabular foundation models that focuses on converting queries, keys, and values to FP8 and employing explicit FP8 matrix multiplication to accelerate attention calculations. It emphasizes aligning quantization errors between training and test rows to avoid accuracy loss, and demonstrates up to 1.7× speedup over 16‑bit kernels with no significant accuracy degradation on TabPFN‑v3 and TabICLv2 across TabArena and BeyondArena.

By Jonas M. K\"ubler, Benjamin J\"ager, Klemens Fl\"oge, Noah Hollmann, Frank Hutter
arXiv Machine Learning
Sep 10

Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method

Squeeze10-LLM is a staged mixed‑precision post‑training quantization framework that reduces 16‑bit LLM weights to an average of 1.6 bits per weight by assigning 80% of weights to 1 bit and 20% to 4 bits. It introduces Post‑Binarization Activation Robustness (PBAR), a weight significance metric that considers activation impact, and Full Information Activation Supervision (FIAS), a strategy that preserves activation information to limit error propagation. Experiments on LLaMA and LLaMA2 demonstrate that Squeeze10‑LLM achieves state‑of‑the‑art performance for sub‑2‑bit weight‑only quantization, raising average accuracy from 43% to 56% on six zero‑shot classification tasks.

By Qingcheng Zhu, Yangyang Ren, Linlin Yang, Yanjing Li, Sheng Xu, Haodong Zhu, Juan Zhang, Runqi Wang, Baochang Zhang