Related papers: Analyzing Quantization in TVM
Quantization for deep neural networks (DNN) have enabled developers to deploy models with less memory and more efficient low-power inference. However, not all DNN designs are friendly to quantization. For example, the popular Mobilenet…
Mixed-precision quantization, where a deep neural network's layers are quantized to different precisions, offers the opportunity to optimize the trade-offs between model size, latency, and statistical accuracy beyond what can be achieved…
Model compression is instrumental in optimizing deep neural network inference on resource-constrained hardware. The prevailing methods for network compression, namely quantization and pruning, have been shown to enhance efficiency at the…
Recently, video language models (VLMs) have been applied in various fields. However, the visual token sequence of the VLM is too long, which may cause intolerant inference latency and GPU memory usage. Existing methods propose…
Despite the superior performance, Large Language Models~(LLMs) require significant computational resources for deployment and use. To overcome this issue, quantization methods have been widely applied to reduce the memory footprint of LLMs…
Large Vision and Language Models have exhibited remarkable human-like intelligence in tasks such as natural language comprehension, problem-solving, logical reasoning, and knowledge retrieval. However, training and serving these models…
In the quest for next-generation sequence modeling architectures, State Space Models (SSMs) have emerged as a potent alternative to transformers, particularly for their computational efficiency and suitability for dynamical systems. This…
Visual Mamba networks (ViMs) extend the selective state space model (Mamba) to various vision tasks and demonstrate significant potential. As a promising compression technique, vector quantization (VQ) decomposes network weights into…
Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of…
Efficient model inference is an important and practical issue in the deployment of deep neural network on resource constraint platforms. Network quantization addresses this problem effectively by leveraging low-bit representation and…
This paper proposes a training method having multiple cyclic training for achieving enhanced performance in low-bit quantized convolutional neural networks (CNNs). Quantization is a popular method for obtaining lightweight CNNs, where the…
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…
Quantization reduces the precision of deep neural networks to lower model size and computational demands, but often at the expense of accuracy. Fully quantized models can suffer significant accuracy degradation, and resource-constrained…
Neural network training is a memory- and compute-intensive task. Quantization, which enables low-bitwidth formats in training, can significantly mitigate the workload. To reduce quantization error, recent methods have developed new data…
As neural networks gain widespread adoption in embedded devices, there is a need for model compression techniques to facilitate deployment in resource-constrained environments. Quantization is one of the go-to methods yielding…
Quantization plays a critical role in digital signal processing systems, allowing the representation of continuous amplitude signals with a finite number of bits. However, accurately representing signals requires a large number of…
Reducing bit-widths of weights, activations, and gradients of a Neural Network can shrink its storage size and memory usage, and also allow for faster training and inference by exploiting bitwise operations. However, previous attempts for…
Large Vision Language Models (LVLMs) have achieved remarkable success in a range of downstream tasks that require multimodal interaction, but their capabilities come with substantial computational and memory overhead, which hinders…
Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…
This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may…