Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters

Zhiyu Guo, Hidetaka Kamigaito, Taro Watanabe


Anthology ID:
2024.emnlp-main.1178
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
21158–21166
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1178
DOI:
Bibkey:
Cite (ACL):
Zhiyu Guo, Hidetaka Kamigaito, and Taro Watanabe. 2024. Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21158–21166, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters (Guo et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1178.pdf