2 citations · 10 across the 13 of their papers we have counts for
14 papers
DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction
Aozhong Zhang, Selcuk Gurses, Yanxia Deng +8
Key-value (KV) cache management has become a critical bottleneck for scaling Large Language Models (LLMs) to long-context scenarios due to linear memory growth. While recent evicti…
Muon: Boosting Muon via Adaptive Second-Moment Preconditioning
Ziyue Liu, Ruijie Zhang, Zhengyang Wang +4
Muon has emerged as a promising optimizer for large-scale foundation model pre-training by exploiting the matrix structure of neural network updates through iterative orthogonaliza…
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
Aozhong Zhang, Naigang Wang, Yanxia Deng +3
In this paper, we present a simple optimization-based preprocessing technique called Weight Magnitude Reduction (MagR) to improve the performance of post-training quantization. For…
CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
Zi Yang, Ziyue Liu, Samridhi Choudhary +4
Training large AI models such as LLMs and DLRMs costs massive GPUs and computing time. The high training cost has become only affordable to big tech companies, meanwhile also causi…
COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
Aozhong Zhang, Zi Yang, Naigang Wang +4
Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing t…
Diagonal Gaussian Mixture Models and Higher Order Tensor Decompositions
Bingni Guo, Jiawang Nie, Zi Yang
This paper studies how to recover parameters in diagonal Gaussian mixture models using tensors. High-order moments of the Gaussian mixture model are estimated from samples. They fo…