model quantization

279 papers

Explore in graph

Also known as

PTQ INT8 QDNN

Co-occurring keywords

model compression (3283) large language model (12755) knowledge distillation (3680) weight quantization (133) post-training quantization (124) neural network optimization (1293) efficient computing (779) neural network (6616) activation quantization (47) efficient inference (225)

Papers

Hyperspherical Quantization: Toward Smaller and More Accurate Models WACV 2023

EQ-Net: Elastic Quantization Neural Networks ICCV 2023

SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations ICCV 2023

Adaptive Data-Free Quantization CVPR 2023

NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization CVPR 2023

OMPQ: Orthogonal Mixed Precision Quantization AAAI 2023

LLM-FP4: 4-Bit Floating-Point Quantized Transformers EMNLP 2023

The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models EMNLP 2023

EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs EMNLP 2023

Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models ACL 2023

PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models ACL 2023

GWQ: Group-Wise Quantization Framework for Neural Networks ACML 2023

Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-Width Deep Neural Networks WACV 2023

Hard Sample Matters a Lot in Zero-Shot Quantization CVPR 2023

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective CVPR 2023

Lossless 4-bit Quantization of Architecture Compressed Conformer ASR Systems on the 300-hr Switchboard Corpus INTERSPEECH 2023

pNLP-Mixer: an Efficient all-MLP Architecture for Language ACL 2023

Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing NIPS 2023

Intriguing Properties of Quantization at Scale NIPS 2023

2-bit Conformer quantization for automatic speech recognition INTERSPEECH 2023

Temporal Dynamic Quantization for Diffusion Models NIPS 2023

Towards Efficient and Accurate Winograd Convolution via Full Quantization NIPS 2023

Compressed MoE ASR Model Based on Knowledge Distillation and Quantization INTERSPEECH 2023

I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference ICCV 2023

The case for 4-bit precision: k-bit Inference Scaling Laws ICML 2023