@article{acceleratingllminferencewithflexiblenm,
  title = {Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator},
  author = {Akshat Ramachandran and Souvik Kundu and Arnab Raha and Shamik Kundu and Deepak K. Mathaikutty and Tushar Krishna},
  year = {2025},
  eprint = {2504.14365},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.14365v1},
}