Bao, H., Su, Z., Setyaev, A., Kamenev, S., Gneushev, A., Zhao, K., . . . Hu, Z. (2026). EPLoN: Exploiting Efficient Parallelism with Selective Rematerialization for Lightning Attention on Ascend NPU. Proceedings of the 40th ACM International Conference on Supercomputing, 1040. https://doi.org/10.1145/3797905.3800540
Chicago Style (17th ed.) CitationBao, Han, et al. "EPLoN: Exploiting Efficient Parallelism with Selective Rematerialization for Lightning Attention on Ascend NPU." Proceedings of the 40th ACM International Conference on Supercomputing 2026: 1040. https://doi.org/10.1145/3797905.3800540.
MLA (9th ed.) CitationBao, Han, et al. "EPLoN: Exploiting Efficient Parallelism with Selective Rematerialization for Lightning Attention on Ascend NPU." Proceedings of the 40th ACM International Conference on Supercomputing, 2026, p. 1040, https://doi.org/10.1145/3797905.3800540.