MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference

Item #:

085713-2564

Details

DOI: https://doi.org/10.52202/085713-2564
Author(s): Donghyeon Joo, Helya Hosseini, Ramyad Hadidi, Bahar Asgari
Pages: 84983-85007 (25 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/085713-2564
Author(s): Donghyeon Joo, Helya Hosseini, Ramyad Hadidi, Bahar Asgari
Pages: 84983-85007 (25 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)