ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty.
Meizhi Zhong, Xikai Liu, Chen Zhang, Yikun Lei, Yan Gao, Yao Hu, Kehai Chen, Min Zhang
Browse the full COLING paper archive.
Meizhi Zhong, Xikai Liu, Chen Zhang, Yikun Lei, Yan Gao, Yao Hu, Kehai Chen, Min Zhang
Browse the full COLING paper archive.