2025
Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
Alessandro Pierro, Steven Abreu, Jonathan Timcheck, Philipp Stratmann, Andreas Wild, Sumit Bam Shrestha
ICML 2025poster
Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. These architectures hold promise for streaming applications at the edge, but deployment in resource-constrained environments requires hardware-aware optimizat…