Title

Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models

4 August 2025

Papers citing "Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models"

1 / 1 papers shown

Title
Lightweight error mitigation strategies for post-training N:M activation sparsity in LLMs Shirin Alanova Kristina Kazistova Ekaterina Galaeva Alina Kostromina Vladimir Smirnov Redko Dmitry Alexey Dontsov Maxim Zhelnin Evgeny Burnaev Egor Shvetsov 120 0 0 26 Sep 2025