conftrace_

group-wise quantization

4 papers

Explore in graph

Also known as

GWQ

Co-occurring keywords · papers mentioning both

model quantization (3) model compression (2) mix-precision quantization (1) integer quantization (1) scale factor conversion (1) power-of-two scaling (1) network layer grouping (1) winograd convolution (1) ultra-low precision (1) channel pruning (1)

Papers

TAGQuant: Token-Aware Clustering for Group-Wise Quantization EACL 2026 Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales CVPR 2025 GWQ: Group-Wise Quantization Framework for Neural Networks ACML 2023 Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT AAAI 2020