January 1, 2024· Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
conference-paper
Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters
Authors:Zhiyu GuoHidetaka KamigaitoTaro Watanabe
Abstract
No abstract metadata is available for this record.
Community
0 commentsUse Connect Wallet in the navigation
No discussion yet
Be the first to share a question or observation.