SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models

Han-Byul Kim, Duc N. M. Hoang, Arnav Kundu, Mohammad Samragh, Minsik Cho. SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models. In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025. OpenReview.net, 2025. [doi]

Abstract

Abstract is missing.