5 papers
SpecMD: A Comprehensive Study On Speculative Expert Prefetching
Duc Hoang, Ajay Jaiswal, Mohammad Samragh +1
Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model's parameters is used during each inference. However, to translate this spar…
MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers
Ajay Jaiswal, Lauren Hannah, Han-Byul Kim +4
Understanding how transformer components operate in LLMs is important, as it is at the core of recent technological advances in artificial intelligence. In this work, we revisit th…
SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models
Han-Byul Kim, Duc Hoang, Arnav Kundu +2
With the rapid expansion in the scale of large language models (LLMs), enabling efficient distributed inference across multiple computing units has become increasingly critical. Ho…
Delay and Overhead Efficient Transmission Scheduling for Federated Learning in UAV Swarms
Duc N. M. Hoang, Vu Tuan Truong, Hung Duy Le +1
This paper studies the wireless scheduling design to coordinate the transmissions of (local) model parameters of federated learning (FL) for a swarm of unmanned aerial vehicles (UA…
Do Compressed LLMs Forget Knowledge? An Experimental Study with Practical Implications
Duc N. M Hoang, Minsik Cho, Thomas Merth +2
Compressing Large Language Models (LLMs) often leads to reduced performance, especially for knowledge-intensive tasks. In this work, we dive into how compression damages LLMs' inhe…