paper-with-me

Papers

ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs

2026-02-06 · Xinlin Li, Timothy Chou, Josh Fromm, Zichang Liu, Yunjie Pan, Christina Fragouli arxiv

Post-training weight quantization is crucial for reducing the memory and inference cost of large language models (LLMs), yet pushing the average precision below 4 bits remains challenging due to highly non-uniform weight sensitivity and the lack of principled precision allocation. Existing solutions use irregular fine-grained mixed-precision with high runtime overhead or rely on heuristics or highly constrained precision allocation strategies. In this work, we propose ScaleBITS, a mixed-precision quantization framework that enables automated, fine-grained bitwidth allocation under a memory budget while preserving hardware efficiency. Guided by a new sensitivity analysis, we introduce a hardware-aligned, block-wise weight partitioning scheme, powered by bi-directional channel reordering. We formulate global bitwidth allocation as a constrained optimization problem and develop a scalable approximation to the greedy algorithm, enabling end-to-end principled allocation. Experiments show that ScaleBITS significantly improves over uniform-precision quantization (up to +36%) and outperforms state-of-the-art sensitivity-aware baselines (up to +13%) in ultra-low-bit regime, without adding runtime overhead.

📄 PDF Abstract BibTeX arXiv:2602.17698

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SDQ: Stochastic Differentiable Quantization with Mixed Precision

2022-06-09 · Xijie Huang, Zhiqiang Shen, Shichao Li, Zechun Liu 외

In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitwidth arithmetic operations, recent resea…

Knowledge DistillationNeural Architecture SearchQuantization

Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators

2021-06-11 · Yonggan Fu, Yongan Zhang, Yang Zhang, David Cox 외

While maximizing deep neural networks' (DNNs') acceleration efficiency requires a joint search/design of three different yet highly coupled aspects, including the networks, bitwidths, and accelerators, the challenges ass…

Efficient Bitwidth Search for Practical Mixed Precision Neural Network

2020-03-17 · Yuhang Li, Wei Wang, Haoli Bai, Ruihao Gong 외

Network quantization has rapidly become one of the most widely used methods to compress and accelerate deep neural networks. Recent efforts propose to quantize weights and activations from different layers with different…

Quantization

Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization

2022-02-23 · Jaehong Yoon, Geon Park, Wonyong Jeong, Sung Ju Hwang

In practical federated learning scenarios, the participating devices may have different bitwidths for computation and memory storage by design. However, despite the progress made in device-heterogeneous federated learnin…

Federated Learning

SigmaQuant: Hardware-Aware Heterogeneous Quantization Method for Edge DNN Inference

2026-02-25 · Qunyou Liu, Pengbo Yu, Marina Zapater, David Atienza arxiv

Deep neural networks (DNNs) are essential for performing advanced tasks on edge or mobile devices, yet their deployment is often hindered by severe resource constraints, including limited memory, energy, and computationa…