Loki: Low-rank Keys for Efficient Sparse Attention

Item #:

079017-0532

Details

DOI: https://doi.org/10.52202/079017-0532
Author(s): Abhinav Bhatele, Soheil Feizi, Shwai He, Siddharth Singh, Prajwal Singhania
Pages: 16692-16723 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-0532
Author(s): Abhinav Bhatele, Soheil Feizi, Shwai He, Siddharth Singh, Prajwal Singhania
Pages: 16692-16723 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)