%0 Journal Article %1 gerami2024fast %A Gerami, Armin %A Hoover, Monte %A Dulepet, Pranav S. %A Duraiswami, Ramani %D 2024 %K LLM attention factorization matrix %T FAST: Factorizable Attention for Speeding up Transformers

@article{gerami2024fast, added-at = {2024-03-28T16:33:51.000+0100}, archiveprefix = {arXiv}, author = {Gerami, Armin and Hoover, Monte and Dulepet, Pranav S. and Duraiswami, Ramani}, biburl = {https://www.bibsonomy.org/bibtex/2bd6755cae9421b0dec9fb563abc66141/randychs}, description = {FAST: Factorizable Attention for Speeding up Transformers}, eprint = {2402.07901}, interhash = {41abbbd80487b671736c0c58b983c814}, intrahash = {bd6755cae9421b0dec9fb563abc66141}, keywords = {LLM attention factorization matrix}, primaryclass = {cs.LG}, timestamp = {2024-03-28T16:34:27.000+0100}, title = {FAST: Factorizable Attention for Speeding up Transformers}, year = 2024 }