Younghoon Byun, Youngjoo Lee. Partially-Structured Transformer Pruning with Patch-Limited XOR-Gate Compression for Stall-Free Sparse-Model Access. In Vivek De, editor, Proceedings of the 61st ACM/IEEE Design Automation Conference, DAC 2024, San Francisco, CA, USA, June 23-27, 2024. ACM, 2024. [doi]
@inproceedings{ByunL24,
title = {Partially-Structured Transformer Pruning with Patch-Limited XOR-Gate Compression for Stall-Free Sparse-Model Access},
author = {Younghoon Byun and Youngjoo Lee},
year = {2024},
doi = {10.1145/3649329.3655677},
url = {https://doi.org/10.1145/3649329.3655677},
researchr = {https://researchr.org/publication/ByunL24},
cites = {0},
citedby = {0},
booktitle = {Proceedings of the 61st ACM/IEEE Design Automation Conference, DAC 2024, San Francisco, CA, USA, June 23-27, 2024},
editor = {Vivek De},
publisher = {ACM},
isbn = {979-8-4007-0601-1},
}