@inproceedings{NEURIPS2022_67d57c32, author = {Dao, Tri and Fu, Dan and Ermon, Stefano and Rudra, Atri and R\'{e}, Christopher}, booktitle = {Advances in Neural Information Processing Systems}, editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh}, pages = {16344--16359}, publisher = {Curran Associates, Inc.}, title = {FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness}, url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/67d57c32e20fd0a7a302cb81d36e40d5-Paper-Conference.pdf}, volume = {35}, year = {2022} }