Related papers: RobuQ: Pushing DiTs to W1.58A2 via Robust Activati…

Diffusion models achieve high-quality image generation but face deployment challenges due to their high computational requirements. Although 8-bit outlier-aware post-training quantization (PTQ) matches full-precision performance, extending…

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…

Neural networks commonly execute on hardware accelerators such as NPUs and GPUs for their size and computation overhead. These accelerators are costly and it is hard to scale their resources to handle real-time workload fluctuations. We…

Diffusion Transformers (DiT) have become a leading architecture in image generation. However, the quadratic complexity of attention mechanisms, which are responsible for modeling token-wise relationships, results in significant latency when…

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…

Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks. To alleviate this inefficiency, we propose \textbf{FastCache}, a…

Diffusion transformers have demonstrated strong capabilities in generating high-quality images. However, as model size increases, the growing memory footprint and inference latency pose significant challenges for practical deployment.…

Operating deep neural networks on devices with limited resources requires the reduction of their memory footprints and computational requirements. In this paper we introduce a training method, called look-up table quantization, LUT-Q, which…

Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful…

The binarization of vision transformers (ViTs) offers a promising approach to addressing the trade-off between high computational/storage demands and the constraints of edge-device deployment. However, existing binary ViT methods often…

Pre-trained Transformer models such as BERT have shown great success in a wide range of applications, but at the cost of substantial increases in model complexity. Quantization-aware training (QAT) is a promising method to lower the…

Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization errors. Prior transform-based mitigations (e.g., Hadamard…

Diffusion-based methods have been acknowledged as a powerful paradigm for end-to-end visuomotor control in robotics. Most existing approaches adopt a Diffusion Policy in U-Net architecture (DP-U), which, while effective, suffers from…

Quantizing neural networks is one of the most effective methods for achieving efficient inference on mobile and embedded devices. In particular, mixed precision quantized (MPQ) networks, whose layers can be quantized to different bitwidths,…

Deep neural network (DNN) quantization converting floating-point (FP) data in the network to integers (INT) is an effective way to shrink the model size for memory saving and simplify the operations for compute acceleration. Recently,…

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…

We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training scaled DiTs ranging from 0.3B upto 8B parameters on…

Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the high computational requirements of ViTs hinder their widespread…

Quantization-aware training (QAT) is a common paradigm for network quantization, in which the training phase incorporates the simulation of the low-precision computation to optimize the quantization parameters in alignment with the task…

Modern pre-trained transformers have rapidly advanced the state-of-the-art in machine learning, but have also grown in parameters and computational complexity, making them increasingly difficult to deploy in resource-constrained…