Cover Image

Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Jung Hyun, Shin, Seungjae, Kim, Vinnam, You, Jaeseong, Chen, An
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Optimizing Large Language Models through Quantization: A Comparative Analysis of PTQ and QAT Techniques
by: Hasan, Jahid
Published: (2024)

FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
by: Lee, Jung Hyun, et al.
Published: (2023)

Pack-PTQ: Advancing Post-training Quantization of Neural Networks by Pack-wise Reconstruction
by: Li, Changjun, et al.
Published: (2025)

FraQAT: Quantization Aware Training with Fractional bits
by: Morreale, Luca, et al.
Published: (2025)

How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training
by: You, Jaeseong, et al.
Published: (2024)

Two-Stage Grid Optimization for Group-wise Quantization of LLMs
by: Kim, Junhan, et al.
Published: (2026)

StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths
by: Chen, Tianyi, et al.
Published: (2026)

Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devices
by: Lee, Hayun, et al.
Published: (2024)

AdaQAT: Adaptive Bit-Width Quantization-Aware Training
by: Gernigon, Cédric, et al.
Published: (2024)

Attn-QAT: 4-Bit Attention With Quantization-Aware Training
by: Zhang, Peiyuan, et al.
Published: (2026)

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
by: Chen, Mengzhao, et al.
Published: (2024)

LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
by: Lee, Jung Hyun, et al.
Published: (2026)

Safety-Preserving PTQ via Contrastive Alignment Loss
by: Wee, Sunghyun, et al.
Published: (2025)

PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
by: Liu, Xuewen, et al.
Published: (2026)

GranQ: Efficient Channel-wise Quantization via Vectorized Pre-Scaling for Zero-Shot QAT
by: Hong, Inpyo, et al.
Published: (2025)

EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams
by: Kim, Jaeseong, et al.
Published: (2026)

Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
by: Xia, Haojun, et al.
Published: (2025)

DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization
by: Jiang, Yanfeng, et al.
Published: (2024)

PTQ4VM: Post-Training Quantization for Visual Mamba
by: Cho, Younghyun, et al.
Published: (2024)

AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation
by: Deb, Prantik, et al.
Published: (2026)

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

Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
by: Kim, Joeun, et al.
Published: (2026)

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

A Case Study of Selected PTQ Baselines for Reasoning LLMs on Ascend NPU
by: Luo, Yuchen, et al.
Published: (2026)

Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
by: Kim, Bumjun, et al.
Published: (2025)

Edge-FIT: Federated Instruction Tuning of Quantized LLMs for Privacy-Preserving Smart Home Environments
by: Venkatesh, Vinay, et al.
Published: (2025)

RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy
by: Lee, Geonho, et al.
Published: (2024)

DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models
by: Ke, Wenjin, et al.
Published: (2025)

Channel-wise Vector Quantization
by: Song, Wei, et al.
Published: (2026)

D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
by: Yan, Xianglong, et al.
Published: (2026)

SDQ-LLM: Sigma-Delta Quantization for 1-bit LLMs of any size
by: Xia, Junhao, et al.
Published: (2025)

Semantic Guidance Tuning for Text-To-Image Diffusion Models
by: Kang, Hyun, et al.
Published: (2023)

Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
by: Yang, Shu, et al.
Published: (2025)

InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs
by: Zhou, Zhongyi, et al.
Published: (2023)

4bit-Quantization in Vector-Embedding for RAG
by: Jeong, Taehee
Published: (2025)

PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models
by: Zhao, Jiaqi, et al.
Published: (2025)

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
by: Yun, Taewon, et al.
Published: (2026)

CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
by: Park, Gunho, et al.
Published: (2025)

UMIE: Unified Multimodal Information Extraction with Instruction Tuning
by: Sun, Lin, et al.
Published: (2024)

TiVaT: A Transformer with a Single Unified Mechanism for Capturing Asynchronous Dependencies in Multivariate Time Series Forecasting
by: Ha, Junwoo, et al.
Published: (2024)