Related papers: SQuAT: Sharpness- and Quantization-Aware Training …

Large language models (LLMs) excel at natural language tasks but face deployment challenges due to their growing size outpacing GPU memory advancements. Model quantization mitigates this issue by lowering weight and activation precision,…

Language Models (LLMs) are often quantized to lower precision to reduce the memory cost and latency in inference. However, quantization often degrades model performance, thus fine-tuning is required for various down-stream tasks.…

Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-end training on the entire dataset, which suffers from long…

In recent years Deep Neural Networks (DNNs) have been rapidly developed in various applications, together with increasingly complex architectures. The performance gain of these DNNs generally comes with high computational costs and large…

Quantization is a promising approach for reducing the inference time and memory footprint of neural networks. However, most existing quantization methods require access to the original training dataset for retraining during quantization.…

Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that repeat the quantization process and train different models…

Quantized networks use less computational and memory resources and are suitable for deployment on edge devices. While quantization-aware training QAT is the well-studied approach to quantize the networks at low precision, most research…

Transformer-based models have gained widespread popularity in both the computer vision (CV) and natural language processing (NLP) fields. However, significant challenges arise during post-training linear quantization, leading to noticeable…

Existing deep learning methods have made significant progress in gait representation learning. Quantization can facilitate the application of gait models as a model-agnostic general compression technique. Typically, appearance-based models…

Mixed-precision quantization has been widely applied on deep neural networks (DNNs) as it leads to significantly better efficiency-accuracy tradeoffs compared to uniform quantization. Meanwhile, determining the exact precision of each layer…

We propose a novel 2-stage sub 8-bit quantization aware training algorithm for all components of a 250K parameter feedforward, streaming, state-free keyword spotting model. For the 1st-stage, we adapt a recently proposed quantization…

Post-training quantization (PTQ) reduces a model's memory footprint by mapping full precision weights into low bit weights without costly retraining, but can degrade its downstream performance especially in low 2- to 3-bit settings. We…

Model quantization is widely applied for compressing and accelerating deep neural networks (DNNs). However, conventional Quantization-Aware Training (QAT) focuses on training DNNs with uniform bit-width. The bit-width settings vary across…

Large language models (LLMs) have shown immense potential across various domains, but their high memory requirements and inference costs remain critical challenges for deployment. Post-training quantization (PTQ) has emerged as a promising…

We present unit scaling, a paradigm for designing deep learning models that simplifies the use of low-precision number formats. Training in FP16 or the recently proposed FP8 formats offers substantial efficiency gains, but can lack…

Lately, post-training quantization methods have gained considerable attention, as they are simple to use, and require only a small unlabeled calibration set. This small dataset cannot be used to fine-tune the model without significant…

The sharpness-aware minimization (SAM) algorithm and its variants, including gap guided SAM (GSAM), have been successful at improving the generalization capability of deep neural network models by finding flat local minima of the empirical…

Pre-trained language models such as BERT have shown remarkable effectiveness in various natural language processing tasks. However, these models usually contain millions of parameters, which prevents them from practical deployment on…

Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource-constrained devices.…

Convolutional neural networks (CNNs) have become the dominant neural network architecture for solving visual processing tasks. One of the major obstacles hindering the ubiquitous use of CNNs for inference is their relatively high memory…