Cover Image

Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Lingchao, Fan, Yuwei, Li, Jun, Hu, Chengqiu, Liao, Qichen, Fan, Junyi, Shi, Rui, Miao, Fangzheng
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AMLA: MUL by ADD in FlashAttention Rescaling
by: Liao, Qichen, et al.
Published: (2025)

TP-Aware Dequantization
by: Hoque, Adnan, et al.
Published: (2024)

Dequantization Barriers for Guided Stoquastic Hamiltonians
by: Hamoudi, Yassine, et al.
Published: (2026)

Dequantization and Hardness of Spectral Sum Estimation
by: Edenhofer, Roman, et al.
Published: (2025)

AXELRAM: Quantize Once, Never Dequantize
by: Nishida, Yasushi
Published: (2026)

Dequantization and Color Transfer with Diffusion Models
by: Vavilala, Vaibhav, et al.
Published: (2023)

Dequantizing Short-Path Quantum Algorithms
by: Gall, François Le, et al.
Published: (2026)

Fast NF4 Dequantization Kernels for Large Language Model Inference
by: Qi, Xiangbo, et al.
Published: (2026)

Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization
by: Li, Jinhao, et al.
Published: (2023)

Improving Detail in Pluralistic Image Inpainting with Feature Dequantization
by: Park, Kyungri, et al.
Published: (2024)

On the Quantization-Dequantization Correspondence for (co)Poisson Hopf Algebras
by: Rivezzi, Andrea, et al.
Published: (2026)

A Dequantized Algorithm for the Guided Local Hamiltonian Problem
by: Zhang, Yukun, et al.
Published: (2024)

On Dequantization of Supervised Quantum Machine Learning via Random Fourier Features
by: Sahebi, Mehrad, et al.
Published: (2025)

New Limits on Distributed Quantum Advantage: Dequantizing Linear Programs
by: Balliu, Alkida, et al.
Published: (2025)

Dequantizing quantum machine learning models using tensor networks
by: Shin, Seongwook, et al.
Published: (2023)

Dequantization of a signal from two parallel quantized observations
by: Kovanda, Vojtěch, et al.
Published: (2024)

DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic
by: Shalby, Hazem Hesham Yousef, et al.
Published: (2025)

Tensor Network Formulation of Dequantized Algorithms for Ground State Energy Estimation
by: Manabe, Hidetaka, et al.
Published: (2025)

Robust Dequantization of the Quantum Singular value Transformation and Quantum Machine Learning Algorithms
by: Gall, François Le
Published: (2023)

LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model
by: Shao, Wei, et al.
Published: (2025)

On the quantum computational complexity of classical linear dynamics with geometrically local interactions: Dequantization and universality
by: Sakamoto, Kazuki, et al.
Published: (2025)

Quantum Inspiration, Classical Advantage: Dequantized particle algorithm for the nonlinear Vlasov-Poisson system
by: Qin, Hong, et al.
Published: (2025)

Energy-Efficient and Dequantization-Free Q-LLMs: A Spiking Neural Network Approach to Salient Value Mitigation
by: Wang, Chenyu, et al.
Published: (2025)

Dequantizing the Quantum Singular Value Transformation: Hardness and Applications to Quantum Chemistry and the Quantum PCP Conjecture
by: Gharibian, Sevag, et al.
Published: (2021)

SteeringDiffusion: A Bottlenecked Activation Control Interface for Diffusion Models
by: Wu, Fangzheng, et al.
Published: (2026)

Online Pseudo-average Shifting Attention(PASA) for Robust Low-precision LLM Inference: Algorithms and Numerical Analysis
by: Cheng, Long, et al.
Published: (2025)

AIS: Adaptive Importance Sampling for Quantized RL
by: Zhou, Jiajun, et al.
Published: (2026)

Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
by: Bu, Tianci, et al.
Published: (2026)

PackInfer: Compute- and I/O-Efficient Attention for Batched LLM Inference
by: Ning, Rui, et al.
Published: (2026)

LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
by: Liu, Yuhan, et al.
Published: (2025)

Scaling LLM Inference Beyond Amdahl`s Limits via Eliminating Non-Scalable Overheads
by: Zhao, Alan, et al.
Published: (2026)

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
by: Fu, Qichen, et al.
Published: (2024)

QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition
by: Hu, Yuxuan, et al.
Published: (2025)

Understanding Bottlenecks for Efficiently Serving LLM Inference With KV Offloading
by: Meng, William, et al.
Published: (2025)

Bias-Corrected Joint Spectral Embedding for Multilayer Networks with Invariant Subspace: Entrywise Eigenvector Perturbation and Inference
by: Xie, Fangzheng
Published: (2024)

iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference
by: Fan, Wei, et al.
Published: (2025)

WaferLLM: Large Language Model Inference at Wafer Scale
by: He, Congjie, et al.
Published: (2025)

Flexible Concept Bottleneck Model
by: Du, Xingbo, et al.
Published: (2025)

DISC: Dynamic Decomposition Improves LLM Inference Scaling
by: Light, Jonathan, et al.
Published: (2025)

CD1a affects the recurrence and prognosis of ovarian cancer
by: Qiong Zhu, et al.
Published: (2024)