Imagen de Portada

Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cook, Jack, Guo, Junxian, Xiao, Guangxuan, Lin, Yujun, Wyss, Keith, Nazemi, Mahdi, Mishra, Asit, del Mundo, Carlo, Blankevoort, Tijmen, Han, Song
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization
por: Bao, Chengzhu, et al.
Publicado: (2026)

Adaptive Block-Scaled Data Types
por: Cook, Jack, et al.
Publicado: (2026)

Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery
por: Xin, Meng, et al.
Publicado: (2026)

Pruning vs Quantization: Which is Better?
por: Kuzmin, Andrey, et al.
Publicado: (2023)

Optimizing Mixture of Block Attention
por: Xiao, Guangxuan, et al.
Publicado: (2025)

FP8 Quantization: The Power of the Exponent
por: Kuzmin, Andrey, et al.
Publicado: (2022)

Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
por: Kopiczko, Dawid J., et al.
Publicado: (2026)

XAttention: Block Sparse Attention with Antidiagonal Scoring
por: Xu, Ruyi, et al.
Publicado: (2025)

Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs
por: Kopiczko, Dawid J., et al.
Publicado: (2024)

VeRA: Vector-based Random Matrix Adaptation
por: Kopiczko, Dawid J., et al.
Publicado: (2023)

Pretraining Large Language Models with NVFP4
por: NVIDIA, et al.
Publicado: (2025)

GPTVQ: The Blessing of Dimensionality for LLM Quantization
por: van Baalen, Mart, et al.
Publicado: (2024)

MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations
por: Zou, Jiaxiang, et al.
Publicado: (2026)

ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
por: Meng, Haoqian, et al.
Publicado: (2026)

NeuroBlend: Towards Low-Power yet Accurate Neural Network-Based Inference Engine Blending Binary and Fixed-Point Convolutions
por: Fayyazi, Arash, et al.
Publicado: (2023)

Sensitivity-Aware Mixed-Precision Quantization and Width Optimization of Deep Neural Networks Through Cluster-Based Tree-Structured Parzen Estimation
por: Azizi, Seyedarmin, et al.
Publicado: (2023)

FAAR: Format-Aware Adaptive Rounding for NVFP4
por: Li, Hanglin, et al.
Publicado: (2026)

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
por: Xiao, Guangxuan, et al.
Publicado: (2022)

Accurate Block Quantization in LLMs with Outliers
por: Trukhanov, Nikita, et al.
Publicado: (2024)

RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping
por: Chen, Yuzong, et al.
Publicado: (2025)

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
por: Liu, Zechun, et al.
Publicado: (2025)

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
por: Panferov, Andrei, et al.
Publicado: (2026)

Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding
por: Bergner, Benjamin, et al.
Publicado: (2024)

Elastic ViTs from Pretrained Models without Retraining
por: Simoncini, Walter, et al.
Publicado: (2025)

InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning
por: Bejnordi, Babak Ehteshami, et al.
Publicado: (2024)

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
por: Lin, Yujun, et al.
Publicado: (2024)

Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy
por: Azizi, Seyedarmin, et al.
Publicado: (2024)

TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
por: Chen, Yuxiang, et al.
Publicado: (2025)

Adapted Center and Scale Prediction: More Stable and More Accurate
por: Wang, Wenhao, et al.
Publicado: (2020)

Dynamic Motions of Ion Acoustic Waves in Plasmas with Superthermal Electrons
por: Asit Saha
Publicado: (2015)

Solitonic, Periodic and Quasiperiodic Behaviors of Dust Ion Acoustic Waves in Superthermal Plasmas
por: Asit Saha
Publicado: (2015)

Bifurcation and Quasiperiodic Behaviors of Ion Acoustic Waves in Magnetoplasmas with Nonthermal Electrons Featuring Tsallis Distribution
por: Asit Saha
Publicado: (2015)

The LLM Surgeon
por: van der Ouderaa, Tycho F. A., et al.
Publicado: (2023)

Dissecting Outlier Dynamics in LLM NVFP4 Pretraining
por: Dong, Peijie, et al.
Publicado: (2026)

Biological activities (antibacterial, antifungal and cytotoxic) of secondary metabolites of Ircinia spp.
por: Nazemi, Melika
Publicado: (2013)

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
por: Yang, Shang, et al.
Publicado: (2025)

Recipes for Pre-training LLMs with MXFP8
por: Mishra, Asit, et al.
Publicado: (2025)

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner
por: Xia, Mengfei, et al.
Publicado: (2023)

Simposio: Educación, convivencia e instituciones. Pilares de una visión compartida
por: Mabel Mundó
Publicado: (2012)

Análisis crítico de la evolución de la anemia y la deficiencia de micronutrimientos en la población
por: Verónica Mundo
Publicado: (2007)