Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving.
Hui Zeng, Daming Zhao, Pengfei Yang, WenXuan Hou, Tianyang Zheng, Hui Li, Weiye Ji, Jidong Zhai
Browse the full AAAI paper archive.
Hui Zeng, Daming Zhao, Pengfei Yang, WenXuan Hou, Tianyang Zheng, Hui Li, Weiye Ji, Jidong Zhai
Browse the full AAAI paper archive.