João Monteiro 0002, Étienne Marcotte, Pierre-André Noël, Valentina Zantedeschi, David Vázquez 0001, Nicolas Chapados, Christopher Pal, Perouz Taslakian. XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference. In Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen, editors, Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024. pages 15284-15302, Association for Computational Linguistics, 2024. [doi]
@inproceedings{0002MNZ0CPT24,
title = {XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference},
author = {João Monteiro 0002 and Étienne Marcotte and Pierre-André Noël and Valentina Zantedeschi and David Vázquez 0001 and Nicolas Chapados and Christopher Pal and Perouz Taslakian},
year = {2024},
url = {https://aclanthology.org/2024.findings-emnlp.896},
researchr = {https://researchr.org/publication/0002MNZ0CPT24},
cites = {0},
citedby = {0},
pages = {15284-15302},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024},
editor = {Yaser Al-Onaizan and Mohit Bansal and Yun-Nung Chen},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-168-1},
}