一作ACL 2026Poster· Natural Language Processing
EQUIP : EQU ivariant preserving In-Place updates for Efficient Token Pruning
Arun Ramachandran · R Govindarajan · Murali Annavaram · Prakash Raghavendra
摘要
Token-pruning has emerged as a primary focus in large language models (LLMs) to enhance model efficiency while preserving accuracy, especially for large sequence lengths. However, the eviction operation of token-pruning methods causes “holes” in KV tensors, posing two major challenges: (1) The sh...