Li, F., Liu, S., Wu, W., Nie, S., & Wang, J. (2025). KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache.
Chicago Style (17th ed.) CitationLi, Fei, Song Liu, Weiguo Wu, Shiqiang Nie, and Jinyu Wang. KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache. 2025.
MLA (9th ed.) CitationLi, Fei, et al. KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache. 2025.
Warning: These citations may not always be 100% accurate.