Motivating Next-Gen Accelerators with Flexible N: M Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches.
Shirin Alanova, Kristina Kazistova, Ekaterina Galaeva, Alina Kostromina, Vladimir Smirnov, Dmitry Redko, Alexey Dontsov, Maxim Zhelnin, Evgeny Burnaev, Egor Shvetsov
Browse the full ACL paper archive.