Related papers: PROFIT: A Novel Training Method for sub-4-bit Mobi…
Diffusion Models (DM) have revolutionized the text-to-image visual generation process. However, the large computational cost and model footprint of DMs hinders practical deployment, especially on edge devices. Post-training quantization…
Recent convolutional neural network (CNN) development continues to advance the state-of-the-art model accuracy for various applications. However, the enhanced accuracy comes at the cost of substantial memory bandwidth and storage…
Network quantization generally converts full-precision weights and/or activations into low-bit fixed-point values in order to accelerate an inference process. Recent approaches to network quantization further discretize the gradients into…
In low-latency or mobile applications, lower computation complexity, lower memory footprint and better energy efficiency are desired. Many prior works address this need by removing redundant parameters. Parameter quantization replaces…
Diffusion models have achieved great success in image synthesis through iterative noise estimation using deep neural networks. However, the slow inference, high memory consumption, and computation intensity of the noise estimation model…
We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on…
We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the…
Compressing neural networks by quantizing model parameters offers useful trade-off between performance and efficiency. Methods like quantization-aware training and post-training quantization strive to maintain the downstream performance of…
Post-training quantization attracts increasing attention due to its convenience in deploying quantized neural networks. Although rounding-to-nearest remains the prevailing method for DNN quantization, prior research has demonstrated its…
Despite the outstanding performance of transformers in both language and vision tasks, the expanding computation and model size have increased the demand for efficient deployment. To address the heavy computation and parameter drawbacks,…
Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is especially useful for memory-intensive recurrent neural…
Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases. Here, we present a…
We present accumulator-aware quantization (A2Q), a novel weight quantization method designed to train quantized neural networks (QNNs) to avoid overflow when using low-precision accumulators during inference. A2Q introduces a unique…
Quantizing large language models (LLMs) to 1-bit precision significantly reduces computational costs, but existing quantization techniques suffer from noticeable performance degradation when using weight and activation precisions below 4…
Fully quantized training (FQT), which uses low-bitwidth hardware by quantizing the activations, weights, and gradients of a neural network model, is a promising approach to accelerate the training of deep neural networks. One major…
Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision…
Weight and activation binarization is an effective approach to deep neural network compression and can accelerate the inference by leveraging bitwise operations. Although many binarization methods have improved the accuracy of the model by…
Convolutional neural networks (CNNs) are crucial for computer vision tasks on resource-constrained devices. Quantization effectively compresses these models, reducing storage size and energy cost. However, in modern depthwise-separable…
We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and quantization policy, we optimize them in a joint manner. To…
At present, the quantification methods of neural network models are mainly divided into post-training quantization (PTQ) and quantization aware training (QAT). Post-training quantization only need a small part of the data to complete the…