paper-with-me

Papers

UWC: Unit-wise Calibration Towards Rapid Network Compression

2022-01-17 · Chen Lin, Zheyang Li, Bo Peng, Haoji Hu, Wenming Tan, Ye Ren, ShiLiang Pu

This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance. Previous PTQ methods usually reduce compression error via performing layer-by-layer parameters calibration. However, with lower representational ability of extremely compressed parameters (e.g., the bit-width goes less than 4), it is hard to eliminate all the layer-wise errors. This work addresses this issue via proposing a unit-wise feature reconstruction algorithm based on an observation of second order Taylor series expansion of the unit-wise error. It indicates that leveraging the interaction between adjacent layers' parameters could compensate layer-wise errors better. In this paper, we define several adjacent layers as a Basic-Unit, and present a unit-wise post-training algorithm which can minimize quantization error. This method achieves near-original accuracy on ImageNet and COCO when quantizing FP32 models to INT4 and INT3.

📄 PDF Abstract BibTeX arXiv:2201.06376

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression

2026-02-11 · Ammar Ali, Baher Mohammad, Denis Makhov, Dmitriy Shopkhoev 외 arxiv

We present ROCKET, a training-free model compression method that achieves state-of-the-art performance in comparison with factorization, structured-sparsification and dynamic compression baselines. Operating under a glob…

Model Compression

LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression

2026-07-03 · Zhuowen Liu, Longkun Hao, Shiyu Feng, Xiaowen Chang 외 arxiv

The rapid growth in the parameter scale of large language models (LLMs) has created a strong demand for efficient compression techniques. As a hardware-agnostic and highly compatible approach, low-rank compression has be…

OAC: Output-adaptive Calibration for Accurate Post-training Quantization

2024-05-23 · Ali Edalati, Alireza Ghaffari, Mahsa Ghazvini Nejad, Lu Hou 외

Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy required for their inference. Post-trai…

Quantization

Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression

2026-05-26 · Kabir Swain, Sijie Han, Daniel Karl I. Weidele, Mauro Martino 외 arxiv

We propose \textbf{Hurwitz Quaternion Multiplicative Quantization (HQMQ)}, a \textbf{calibration-free} method for KV cache compression of large language models. HQMQ treats each 4-element chunk of K or V as a quaternion …

COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression

2026-02-16 · Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Ammar Ali 외 arxiv

Post-training compression of Transformer models commonly relies on truncated singular value decomposition (SVD). However, enforcing a single shared subspace can degrade accuracy even at moderate compression. Sparse dicti…