PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference.
Dongjie Yang, Xiaodong Han, Yan Gao, Yao Hu, Shilin Zhang, Hai Zhao
Browse the full ACL paper archive.
Dongjie Yang, Xiaodong Han, Yan Gao, Yao Hu, Shilin Zhang, Hai Zhao
Browse the full ACL paper archive.