3 citations · 3 across the 8 of their papers we have counts for
4 papers · 1 filter
Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization
Bahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh +2
Efficient autoregressive generation is increasingly limited by the memory footprint of the key-value (KV) cache, which grows linearly with sequence length, batch size, and model de…
EPAS: Efficient Training with Progressive Activation Sharing
Rezaul Karim, Maryam Dialameh, Yang Liu +2
We present a novel method for Efficient training with Progressive Activation Sharing (EPAS). This method bridges progressive training paradigm with the phenomenon of redundant QK (…
Bayesian Mixture of Experts For Large Language Models
Maryam Dialameh, Hossein Rajabzadeh, Weiwei Zhang +2
We present Bayesian Mixture of Experts (Bayesian-MoE), a post-hoc uncertainty estimation framework for fine-tuned large language models (LLMs) based on Mixture-of-Experts architect…
ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training
Maryam Dialameh, Rezaul Karim, Hossein Rajabzadeh +5
This paper introduces ECHO-LLaMA, an efficient LLaMA architecture designed to improve both the training speed and inference throughput of LLaMA architectures while maintaining its…