Search Results for author:
Found 14 papers, 5 papers with code
QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
We introduce QUICK, a group of novel optimized CUDA kernels for the efficient inference of quantized Large Language Models (LLMs).
SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
In this paper, we introduce SLEB, a novel approach designed to streamline LLMs by eliminating redundant transformer blocks.
Squeezing Large-Scale Diffusion Models for Mobile
The emergence of diffusion models has greatly broadened the scope of high-fidelity image synthesis, resulting in notable advancements in both practical implementation and academic research.
OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models
Large language models (LLMs) with hundreds of billions of parameters require powerful server-grade GPUs for inference, limiting their practical deployment.
Temporal Dynamic Quantization for Diffusion Models
The diffusion model has gained popularity in vision applications due to its remarkable generative performance and versatility.
INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold
Binary Neural Networks (BNNs) have emerged as a promising solution for reducing the memory footprint and compute costs of deep neural networks, but they suffer from quality degradation due to the lack of freedom as activations and weights are constrained to the binary values.
Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution
We also show that adjusting the threshold values of binary activation functions results in the unbalanced distribution of the binary activation, which increases the accuracy of BNN models.
SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System
To our best knowledge, our work is the first comprehensive study of a modularized E2E multi-domain dialog system that learning from each component to the entire dialog policy for task success.
Empirical Strategy for Stretching Probability Distribution in Neural-network-based Regression
In this study, we considered the distribution error, i. e., the inconsistency of two distributions (those of the predicted values and label), as the prediction error, and proposed weighted empirical stretching (WES) as a novel loss function to increase the overlap area of the two distributions.
BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations
Binary Neural Networks (BNNs) have been garnering interest thanks to their compute cost reduction and memory savings.
Zero-shifting Technique for Deep Neural Network Training on Resistive Cross-point Arrays
By using this zero-shifting method, we show that network performance dramatically improves for imbalanced synapse devices.
BitSplit-Net: Multi-bit Deep Neural Network with Bitwise Activation Function
We demonstrate that the BitSplit version of LeNet-5, VGG-9, AlexNet, and ResNet-18 can be trained to have similar classification accuracy at a lower computational cost compared to conventional multi-bit networks with low bit precision (<= 4-bit).
Neural Network-Hardware Co-design for Scalable RRAM-based BNN Accelerators
Recently, RRAM-based Binary Neural Network (BNN) hardware has been gaining interests as it requires 1-bit sense-amp only and eliminates the need for high-resolution ADC and DAC.
Deep Neural Network Optimized to Resistive Memory with Nonlinear Current-Voltage Characteristics
Artificial Neural Network computation relies on intensive vector-matrix multiplications.
