Image de couverture de livre

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Egiazarian, Vage, Castro, Roberto L., Kuznedelev, Denis, Panferov, Andrei, Kurtic, Eldar, Pandit, Shubhra, Marques, Alexandre, Kurtz, Mark, Ashkboos, Saleh, Hoefler, Torsten, Alistarh, Dan
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
par: Kurtic, Eldar, et autres
Publié: (2024)

Extreme Compression of Large Language Models via Additive Quantization
par: Egiazarian, Vage, et autres
Publié: (2024)

Grid Games: The Power of Multiple Grids for Quantizing Large Language Models
par: Egiazarian, Vage, et autres
Publié: (2026)

EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
par: Sieberling, Oliver, et autres
Publié: (2024)

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
par: Chen, Jiale, et autres
Publié: (2025)

Beyond Outliers: A Study of Optimizers Under Quantization
par: Vlassis, Georgios, et autres
Publié: (2025)

Statistically-Lossless Quantization of Large Language Models
par: Helcig, Michael, et autres
Publié: (2026)

Quartet: Native FP4 Training Can Be Optimal for Large Language Models
par: Castro, Roberto L., et autres
Publié: (2025)

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models
par: Shutova, Alina, et autres
Publié: (2025)

Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization
par: Egiazarian, Vage, et autres
Publié: (2024)

Unified Scaling Laws for Compressed Representations
par: Panferov, Andrei, et autres
Publié: (2025)

EfQAT: An Efficient Framework for Quantization-Aware Training
par: Ashkboos, Saleh, et autres
Publié: (2024)

Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models
par: Kurtic, Eldar, et autres
Publié: (2024)

Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment
par: Agarwalla, Abhinav, et autres
Publié: (2024)

HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
par: Ashkboos, Saleh, et autres
Publié: (2025)

Apertus LLM Family Expansion via Distillation and Quantization
par: Panferov, Andrei, et autres
Publié: (2026)

Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant
par: Nicolicioiu, Armand, et autres
Publié: (2024)

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
par: Rodionov, Gleb, et autres
Publié: (2025)

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training
par: Tabesh, Soroush, et autres
Publié: (2025)

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
par: Dadgarnia, Alireza, et autres
Publié: (2026)

DarwinLM: Evolutionary Structured Pruning of Large Language Models
par: Tang, Shengkun, et autres
Publié: (2025)

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
par: Malinovskii, Vladimir, et autres
Publié: (2024)

Error Feedback Can Accurately Compress Preconditioners
par: Modoranu, Ionut-Vlad, et autres
Publié: (2023)

DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization
par: Lin, Haokun, et autres
Publié: (2026)

QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
par: Ashkboos, Saleh, et autres
Publié: (2024)

The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
par: Chen, Jiale, et autres
Publié: (2025)

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
par: Panferov, Andrei, et autres
Publié: (2026)

SliceGPT: Compress Large Language Models by Deleting Rows and Columns
par: Ashkboos, Saleh, et autres
Publié: (2024)

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
par: Modoranu, Ionut-Vlad, et autres
Publié: (2024)

Correlated Quantization for Faster Nonconvex Distributed Optimization
par: Panferov, Andrei, et autres
Publié: (2024)

The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
par: Wu, Diyuan, et autres
Publié: (2024)

MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling
par: Zhang, Yu, et autres
Publié: (2025)

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
par: Panferov, Andrei, et autres
Publié: (2025)

MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models
par: Frantar, Elias, et autres
Publié: (2024)

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
par: Zhang, Jintao, et autres
Publié: (2025)

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
par: Malinovskii, Vladimir, et autres
Publié: (2024)

Neural Optimal Transport with General Cost Functionals
par: Asadulaev, Arip, et autres
Publié: (2022)

Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations
par: Li, Shigang, et autres
Publié: (2019)

LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs
par: Gordon, Ofir, et autres
Publié: (2026)

Post Training Quantization of Large Language Models with Microscaling Formats
par: Sharify, Sayeh, et autres
Publié: (2024)