Hao Zhang, Xiaoli Gong, Haoran Li, Huayou Su, Qingxia Chen, Jin Zhang 0003. JSQKV: Joint Sparsification and Quantization for KV-Cache Compression and Decode Acceleration. In Lieven Eeckhout, Chao Li 0009, Zhibin Yu, Avi Mendelson, editors, Advanced Parallel Processing Technologies - 17th International Symposium, APPT 2026, Brussels, Belgium, July 27, 2026, Proceedings. Volume 16693 of Lecture Notes in Computer Science, pages 67-81, Springer, 2026. [doi]
Abstract is missing.