activity
20192026
most citedOliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization

150 citations · 274 across the 69 of their papers we have counts for

collaborators
Showing 2022Show all

7 papers · 1 filter

cs.LG2022

Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training

Cong Guo, Yuxian Qiu, Jingwen Leng +6

An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN). Many novel and sophisticated activation functions have been…

cs.LG2022★ 3 cited

ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization

Cong Guo, Chen Zhang, Jingwen Leng +5

Quantization is a technique to reduce the computation and memory cost of DNN models, which are getting increasingly large. Existing quantization solutions use fixed-point integer o…

cs.LG2022★ 2 cited

Efficient Adaptive Activation Rounding for Post-Training Quantization

Zhengyi Li, Cong Guo, Zhanda Zhu +5

Post-training quantization attracts increasing attention due to its convenience in deploying quantized neural networks. Although rounding-to-nearest remains the prevailing method f…

cs.AR2022★ 1 cited

SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences

Guan Shen, Jieru Zhao, Quan Chen +3

The attention mechanisms of transformers effectively extract pertinent information from the input sequence. However, the quadratic complexity of self-attention w.r.t the sequence l…

cs.CL2022

Transkimmer: Transformer Learns to Layer-wise Skim

Yue Guan, Zhengyi Li, Jingwen Leng +2

Transformer architecture has become the de-facto model for many machine learning tasks from natural language processing and computer vision. As such, improving its computational ef…

cs.LG2022★ 19 cited

SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

Cong Guo, Yuxian Qiu, Jingwen Leng +6

Quantization of deep neural networks (DNN) has been proven effective for compressing and accelerating DNN models. Data-free quantization (DFQ) is a promising approach without the o…