most citedREAP the Experts: Why Pruning Prevails for One-Shot MoE compression

1 citations · 1 across the 1 of their papers we have counts for

collaborators

5 papers

cs.LG20261 cited

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Mike Lasby, Ivan Lazarevich, Nish Sinnadurai +3

Sparsely-activated Mixture-of-Experts (SMoE) models offer efficient pre-training and low latency but their large parameter counts create significant memory overhead, motivating res…

cs.LG2025

TapOut: A Bandit-Based Approach to Dynamic Speculative Decoding

Aditya Sridhar, Nish Sinnadurai, Sean Lie +1

Speculative decoding accelerates LLMs by using a lightweight draft model to generate tokens autoregressively before verifying them in parallel with a larger target model. However,…

cs.CL2025

SD: Self-Distilled Sparse Drafters

Mike Lasby, Nish Sinnadurai, Valavan Manohararajah +3

Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the use of highly compressed…

cs.LG2025

MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models

Mugilan Ganesan, Shane Segal, Ankur Aggarwal +3

Speculative decoding significantly accelerates language model inference by enabling a lightweight draft model to propose multiple tokens that a larger target model verifies simulta…

cs.LG2025

Self-Data Distillation for Recovering Quality in Pruned Large Language Models

Vithursan Thangarasa, Ganesh Venkatesh, Mike Lasby +2

Large language models have driven significant progress in natural language processing, but their deployment requires substantial compute and memory resources. As models scale, comp…