@article{polarsparsityhighthroughputbatchedllm,
  title = {Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity},
  author = {Susav Shrestha and Brad Settlemyer and Nikoli Dryden and Narasimha Reddy},
  year = {2025},
  eprint = {2505.14884},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.14884v1},
}