Cover Image

Block Rotation is All You Need for MXFP4 Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shao, Yuantian, Wang, Peisong, Chen, Yuanteng, Xu, Chang, Wei, Zhihui, Cheng, Jian
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
by: Shao, Yuantian, et al.
Published: (2025)

EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models
by: Chen, Yuanteng, et al.
Published: (2025)

Ban&Pick: Ehancing Performance and Efficiency of MoE-LLMs via Smarter Routing
by: Chen, Yuanteng, et al.
Published: (2025)

Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoE
by: Chen, Yuanteng, et al.
Published: (2026)

IntraSlice: Towards High-Performance Structural Pruning with Block-Intra PCA for LLMs
by: Li, Meng, et al.
Published: (2026)

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
by: Tyukin, Georgy, et al.
Published: (2024)

TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization
by: Xu, Zukang, et al.
Published: (2026)

More Agents Is All You Need
by: Li, Junyou, et al.
Published: (2024)

Tensor Product Attention Is All You Need
by: Zhang, Yifan, et al.
Published: (2025)

Attention Smoothing Is All You Need For Unlearning
by: Zade, Saleh Zare, et al.
Published: (2026)

Attention Is Not All You Need: The Importance of Feedforward Networks in Transformer Models
by: Gerber, Isaac
Published: (2025)

All You Need is One: Capsule Prompt Tuning with a Single Vector
by: Liu, Yiyang, et al.
Published: (2025)

CBQ: Cross-Block Quantization for Large Language Models
by: Ding, Xin, et al.
Published: (2023)

Synthetic Data RL: Task Definition Is All You Need
by: Guo, Yiduo, et al.
Published: (2025)

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
by: Li, Pengyi, et al.
Published: (2025)

Attention Is All You Need for KV Cache in Diffusion LLMs
by: Nguyen-Tri, Quan, et al.
Published: (2025)

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
by: Blumenberg, Patrick, et al.
Published: (2025)

Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design
by: Sun, Lin, et al.
Published: (2025)

Reformulation is All You Need: Addressing Malicious Text Features in DNNs
by: Jiang, Yi, et al.
Published: (2025)

BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization
by: Li, Ji-Fu, et al.
Published: (2026)

Memory Is All You Need: Testing How Model Memory Affects LLM Performance in Annotation Tasks
by: Timoneda, Joan C., et al.
Published: (2025)

Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective
by: He, Shenghua, et al.
Published: (2025)

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!
by: Yoon, Do-hyeon, et al.
Published: (2025)

Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizer
by: Choi, Euntae, et al.
Published: (2025)

SecEncoder: Logs are All You Need in Security
by: Bulut, Muhammed Fatih, et al.
Published: (2024)

One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP Tasks
by: Nehrdich, Sebastian, et al.
Published: (2024)

Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters
by: Guo, Zhiyu, et al.
Published: (2024)

An Extra RMSNorm is All You Need for Fine Tuning to 1.58 Bits
by: Steinmetz, Cody, et al.
Published: (2025)

Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models
by: Gomaa, Eyad, et al.
Published: (2024)

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
by: Wei, Zhepei, et al.
Published: (2026)

Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models
by: Xu, Mingxue, et al.
Published: (2024)

Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling
by: Cook, Jack, et al.
Published: (2025)

Reinforcement Learning is all You Need
by: Lian, Yongsheng
Published: (2025)

You Need Better Attention Priors
by: Litman, Elon, et al.
Published: (2026)

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
by: Su, Zunhai, et al.
Published: (2025)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
by: Xu, Zukang, et al.
Published: (2025)

Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space
by: Zhang, Xiang, et al.
Published: (2025)

Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts
by: Gan, Chunjing, et al.
Published: (2024)

Evidence Is All You Need: Ordering Imaging Studies via Language Model Alignment with the ACR Appropriateness Criteria
by: Yao, Michael S., et al.
Published: (2024)

ToolRL: Reward is All Tool Learning Needs
by: Qian, Cheng, et al.
Published: (2025)